CA2889349C - Methods and apparatus to estimate demographics of users employing social media - Google Patents
Methods and apparatus to estimate demographics of users employing social media Download PDFInfo
- Publication number
- CA2889349C CA2889349C CA2889349A CA2889349A CA2889349C CA 2889349 C CA2889349 C CA 2889349C CA 2889349 A CA2889349 A CA 2889349A CA 2889349 A CA2889349 A CA 2889349A CA 2889349 C CA2889349 C CA 2889349C
- Authority
- CA
- Canada
- Prior art keywords
- asset
- social media
- demographics
- user
- message
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000015654 memory Effects 0.000 claims description 36
- 238000003860 storage Methods 0.000 claims description 36
- 238000005259 measurement Methods 0.000 claims description 13
- 238000010207 Bayesian analysis Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 19
- 239000000047 product Substances 0.000 description 18
- 230000008569 process Effects 0.000 description 17
- 238000004891 communication Methods 0.000 description 11
- 238000007619 statistical method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 239000000203 mixture Substances 0.000 description 7
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 102000004169 proteins and genes Human genes 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 235000013550 pizza Nutrition 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012109 statistical procedure Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Methods, apparatus, systems and articles of manufacture are disclosed to estimate demographics of users employing social media. An example method disclosed herein includes (1) identifying a social media message regarding an asset, the social media message associated with a user identifier associated with the user, (2) determining demographics associated with a group of people exposed to the asset, (3) associating the user identifier with the asset, and (4) repeating (1) to (3). The example method also includes (5) combining demographics associated with two or more different groups of people with which the user identifier is associated to estimate a demographic profile for the user.
Description
METHODS AND APPARATUS TO ESTIMATE DEMOGRAPHICS
OF USERS EMPLOYING SOCIAL MEDIA
RELATED APPLICATION
[0001] This patent claims priority from U.S. Patent Application Serial No.
14/142,411, which is entitled "METHODS AND APPARATUS TO ESTIMATE DEMOGRAPHICS OF
USERS EMPLOYING SOCIAL MEDIA" and was filed on December 27, 2013.
FIELD OF THE DISCLOSURE
OF USERS EMPLOYING SOCIAL MEDIA
RELATED APPLICATION
[0001] This patent claims priority from U.S. Patent Application Serial No.
14/142,411, which is entitled "METHODS AND APPARATUS TO ESTIMATE DEMOGRAPHICS OF
USERS EMPLOYING SOCIAL MEDIA" and was filed on December 27, 2013.
FIELD OF THE DISCLOSURE
[0002] This disclosure relates generally to audience measurement, and, more particularly, to methods and apparatus to estimate demographics of users employing social media.
BACKGROUND
BACKGROUND
[0003] Audience measurement of media (e.g., any type of content and/or advertisements such as broadcast television and/or radio, stored audio and/or video played back from a memory such as a digital video recorder or a digital video disc, a webpage, audio and/or video presented (e.g., streamed) via the Internet, a video game, etc.) often involves collection of media identifying data (e.g., signature(s), fingerprint(s), code(s), tuned channel identification information, time of exposure information, etc.) and people data (e.g., user identifier(s), demographic data associated with audience member(s), etc.). The media identifying data and the people data can be combined to generate, for example, media exposure data indicative of amount(s) and/or type(s) of people that were exposed to specific piece(s) of media.
BRIEF DESCRIPTION OF THE DRAWINGS
BRIEF DESCRIPTION OF THE DRAWINGS
[0004] FIG. 1 is a diagram of an example system constructed in accordance with the teachings of this disclosure to estimate demographics of users employing social media.
[0005] FIG. 2 is an example data table that may be stored by the example audience measurement entity of FIG. 1.
[0006] FIG. 3 is a block diagram of an example implementation of the audience measurement entity server of FIG. 1 that may facilitate estimating demographics of users employing social media.
[0007] FIG. 4 is a block diagram of an example implementation of the tagged identifier logger of FIG. 3 that may facilitate tagging social media user identifiers with asset demographic information.
[0008] FIG. 5 is an example data table storing data representing social media user identifiers tagged with asset demographics that may be collected by the example audience measurement entity server of FIGS. 1, 3 and 4.
[0009] FIG. 6 is a an example data table storing data representing estimated demographics corresponding to social media user identifiers that may be collected by the example audience measurement entity server of FIGS. 1, 3 and 4.
[0010] FIG. 7 is a flowchart representative of example machine-readable instructions that may be executed to estimate demographics of users employing social media.
[0011] FIG. 8 is a flowchart representative of example machine-readable instructions that may be executed to tag user identifiers of social media messages with demographics of assets of interest.
[0012] FIG. 9 is a flowchart representative of example machine-readable instructions that may be executed to generate profiles estimating demographics of users employing social media.
[0013] FIG. 10 is a block diagram of an example processing platform capable of executing the example machine-readable instructions of FIGS. 7-9 to implement the example audience measurement entity server of FIGS. 1, 3 and/or 4.
DETAILED DESCRIPTION
DETAILED DESCRIPTION
[0014] Example methods, systems and apparatus disclosed herein may be used to impute demographic information of a known first group of people onto an unknown second group of people. For example, techniques disclosed herein enable estimating demographics of users employing social media.
[0015] Social messaging has become a widely used medium in which users disseminate and receive information. Online social messaging services (such as Twitter or Facebook) enable users to send social media messages or instant messages to many users at once.
Some social messaging services enable users to "follow" or "friend" other users (e.g., subscribe to receive messages sent by select users (e.g., via the Twitter service), status updates (e.g., via the Facebook service or Google+Tm social service), etc.). For example, a user following (e.g., subscribed to, online friends with, etc.) a celebrity in the Twitter service may receive indications via a client application (e.g., the TweetDeck client application or any other social media messaging client application) when the celebrity sends or posts a social media message.
Some social messaging services enable users to "follow" or "friend" other users (e.g., subscribe to receive messages sent by select users (e.g., via the Twitter service), status updates (e.g., via the Facebook service or Google+Tm social service), etc.). For example, a user following (e.g., subscribed to, online friends with, etc.) a celebrity in the Twitter service may receive indications via a client application (e.g., the TweetDeck client application or any other social media messaging client application) when the celebrity sends or posts a social media message.
[0016] Social media messages (sometimes referred to herein as "messages,"
"statuses,"
"texts" or "tweets") may be used to convey many different types of information. In some examples, social media messages are used to relay general information about a user. For example, a message sender may send a social media message indicating that they are bored. In some examples, social media messages are used to convey information self-reporting activity by the message sender regarding an asset such as a media event, product or service. For example, a message sender may convey a social media message indicating that the message sender is watching a certain television program, listening to a certain song, or just purchased a certain book. Asset-regarding social media messages are social media messages that are disseminated to a mass audience and indicate exposure to the asset. In some examples disclosed herein, social media messages are collected and then filtered to identify asset-regarding social media messages.
"statuses,"
"texts" or "tweets") may be used to convey many different types of information. In some examples, social media messages are used to relay general information about a user. For example, a message sender may send a social media message indicating that they are bored. In some examples, social media messages are used to convey information self-reporting activity by the message sender regarding an asset such as a media event, product or service. For example, a message sender may convey a social media message indicating that the message sender is watching a certain television program, listening to a certain song, or just purchased a certain book. Asset-regarding social media messages are social media messages that are disseminated to a mass audience and indicate exposure to the asset. In some examples disclosed herein, social media messages are collected and then filtered to identify asset-regarding social media messages.
[0017] It is useful, however, to link demographics and/or other user information to the message senders. For example, companies and/or individuals want to understand the reach and exposure of the asset (e.g., a media event, a product and/or a service) that they deliver, produce and/or provide. For example, a media event that is associated with larger numbers of exposure and/or larger numbers of occurrences of an association may be considered more effective at influencing user behavior.
[0018] In some examples, demographics developed for a panel (e.g., a television panel, a loyalty card panel, etc.) are used to infer demographics for users of online social messaging services who send social media messages regarding the same asset such as a media event, a product and/or a service. In some examples, panelist demographics developed for a first media event such as television programs, advertisements, etc. may be used to estimate demographics of users of social media posting contemporaneous messages and/or near contemporaneous messages concerning the media event. For example, time-stamped records identifying exposure to the media event (e.g., television content and/or advertisements) and time-stamped social media messages commenting on the media event are identified. Users who post messages corresponding to (e.g., mentioning and/or referencing) the media of interest (e.g., television content and/or advertisement) within a time window close to (e.g., adjacent, falls within a threshold time of and/or overlapping with) a time window of presentation of the corresponding media are assumed to be in the audience of the referenced media event and, thus, within demographics of the audience of the media event. The demographics for the media event (e.g., an asset of interest) may be identified by, for example, an audience measurement entity (e.g., The Nielsen Company (US), LLC) based on a panel of consumers. The demographics for a single media event (e.g., a particular television show and/or advertisement) may be spread across many demographic segments (e.g., 20% males age 20-25, 25% females age 20-25, 10%
males less than age 20, 3% female less than age 20, 30% males age 40-50, 12% females age 40-50). Therefore, identifying social media users as being in the audience of that single media event provides an indication that the user fits within one of any of these demographic segments (sometimes referred to herein as "demographic buckets," "demographic pools," "demographic categories,"
"demographic composition" or "market breaks"). The percentage composition of the audience may be used as a proxy for the likelihood that the social media user fits into one of the demographic buckets (e.g., a 12% chance the user is female age 40-50). These percentages may be modified based on known social media usage patterns. For example, if females age 40-50 are more likely to use social media than males age 40-50, the percentages of the demographic composition may be weighted or otherwise adjusted to reflect those likelihoods.
males less than age 20, 3% female less than age 20, 30% males age 40-50, 12% females age 40-50). Therefore, identifying social media users as being in the audience of that single media event provides an indication that the user fits within one of any of these demographic segments (sometimes referred to herein as "demographic buckets," "demographic pools," "demographic categories,"
"demographic composition" or "market breaks"). The percentage composition of the audience may be used as a proxy for the likelihood that the social media user fits into one of the demographic buckets (e.g., a 12% chance the user is female age 40-50). These percentages may be modified based on known social media usage patterns. For example, if females age 40-50 are more likely to use social media than males age 40-50, the percentages of the demographic composition may be weighted or otherwise adjusted to reflect those likelihoods.
[0019] While using one user message regarding a media event may not be a precise indicator of the demographics of the social network user given the breadth of demographics associated with such an event, aggregating messages by the same user for multiple media events results in increasing granularity and/or accuracy. For example, statistical methods such as Bayesian analysis may be applied to the different demographic pools associated with different media events for which the same user is known to have sent a social media message (e.g., is known to have been in the audience for the media event) to obtain a more precise demographics estimation of that user. For example, if a second media event for which the social media user sends a message is only 1% female age 40-50, no males age 40-50, and 50% female age 20-25, then joining the set of probabilities for the second media event with the set of probabilities for the first media event for the example above, the likelihood of the social media user being a female aged 40-50 or a male aged 40-50 are decreased and the likelihood of the user being a male age 20-25 is greatly increased.
[0020] Demographic information may be used from different types of panels to estimate the demographics of social media users. For example, demographics from a television panel may be used as explained above. Alternatively, demographics from a consumer purchase panel (e.g., Nielsen's HomescanTM panel, a loyalty card panel, etc.) may be used.
Participants enrolled in HomescanTM scan product identifiers (e.g., barcodes) after purchasing the product. A panelist identifier is associated with the product identifier, and, as the demographics for the panelist are known, demographic information for the corresponding product can be determined. In some examples, demographics for two or more different types of panels are used (e.g., a television panel and the HomescanTM panel). For example, a social media user may send a first message mentioning a television program or a characteristic of a television program and then send a second message mentioning a product (e.g., running shoes) or a characteristic of a product. In some examples, known demographics of viewers of the television program collected via, for example, a television panel, may be combined with known demographics of persons who purchased the running shoes collected via, for example, a HomescanTM panel, to estimate demographics of the social media user.
Participants enrolled in HomescanTM scan product identifiers (e.g., barcodes) after purchasing the product. A panelist identifier is associated with the product identifier, and, as the demographics for the panelist are known, demographic information for the corresponding product can be determined. In some examples, demographics for two or more different types of panels are used (e.g., a television panel and the HomescanTM panel). For example, a social media user may send a first message mentioning a television program or a characteristic of a television program and then send a second message mentioning a product (e.g., running shoes) or a characteristic of a product. In some examples, known demographics of viewers of the television program collected via, for example, a television panel, may be combined with known demographics of persons who purchased the running shoes collected via, for example, a HomescanTM panel, to estimate demographics of the social media user.
[0021] In some examples, certain asset proprietors (e.g., distributors, producers and/or providers of assets such as a retailer (e.g., Amazon.com)) enable a user to post a message (e.g., a tweet, a status update, etc.) after the user has made a purchase. In some examples, when a user elects to post a message, the message may include a specific phrase such as "I
just bought," the asset purchased (e.g., "a box of protein bars"), and an asset proprietor identifier (e.g., "via @Amazon"). In some examples, the asset proprietor may record an identifier (e.g., a Twitter handle) for the user when posting the message. In some such examples, the asset proprietor may associate demographic information with the user informed from past purchases made by the user and/or other users.
just bought," the asset purchased (e.g., "a box of protein bars"), and an asset proprietor identifier (e.g., "via @Amazon"). In some examples, the asset proprietor may record an identifier (e.g., a Twitter handle) for the user when posting the message. In some such examples, the asset proprietor may associate demographic information with the user informed from past purchases made by the user and/or other users.
[0022] In some examples, the asset proprietor may not record an identifier of the social media user when the user posts the message. Example methods disclosed herein identify a set of posted messages associated with the purchase of a particular asset (e.g., an asset of interest such as protein bars), thereby enabling collecting a set of associated user identifiers. Each of the user identifiers may be associated with demographics associated with that particular asset. As discussed above, while one instance of a posted message provides some demographic information regarding the message poster, collecting demographics associated with a plurality of messages posted by the user enables generating a more granular (e.g., specific) and/or more accurate user demographics profile. Thus, examples disclosed herein analyze the plurality of messages over time to predict the demographics associated with a particular user via the user identifiers. In some examples, statistical analysis (e.g., Bayesian analysis, principal component analysis, etc.) is used to develop the demographics estimate. In some examples, different weights are associated with the respective demographics to generate a demographic profile of greater accuracy and precision.
[0023] FIG. 1 is an illustration of an example environment 100 in which examples disclosed herein may be implemented to estimate demographics of users employing social media. The example environment 100 of FIG. 1 includes an audience measurement entity (AME) 102, a message hosting server 104 and an asset proprietor 106. The AME 102 of the illustrated example is an entity that monitors and/or reports posts of social media messages. In the illustrated example of FIG. 1, the AME 102 operates and/or hosts an example AME server 108.
The AME server 108 of the illustrated example is a server and/or database that collects and/or receives social media messages related to assets (e.g., media events, products and/or services) and estimates demographics of the message posters. In some examples, the AME
server 108 is implemented using multiple devices and/or the message hosting server 104 is implemented using multiple devices. For example, the AME server 108 and/or the message hosting server 104 may include disk arrays or multiple workstations (e.g., desktop computers, workstation servers, laptops, etc.) in communication with one another. In the illustrated example, the AME server 108 is in selective communication with the message hosting server 104 and/or the asset proprietor 106 via one or more wired and/or wireless networks represented by network 110.
Example network 110 may be implemented using any suitable wired and/or wireless network(s) including, for example, one or more data buses, one or more Local Area Networks (LANs), one or more wireless LANs, one or more cellular networks, the Internet, etc. As used herein, the phrase "in communication," including variances thereof, encompasses direct communication and/or indirect communication through one or more intermediary components and does not require direct physical (e.g., wired) communication and/or constant communication, but rather additionally includes selective communication at periodic or aperiodic intervals, as well as one-time events.
The AME server 108 of the illustrated example is a server and/or database that collects and/or receives social media messages related to assets (e.g., media events, products and/or services) and estimates demographics of the message posters. In some examples, the AME
server 108 is implemented using multiple devices and/or the message hosting server 104 is implemented using multiple devices. For example, the AME server 108 and/or the message hosting server 104 may include disk arrays or multiple workstations (e.g., desktop computers, workstation servers, laptops, etc.) in communication with one another. In the illustrated example, the AME server 108 is in selective communication with the message hosting server 104 and/or the asset proprietor 106 via one or more wired and/or wireless networks represented by network 110.
Example network 110 may be implemented using any suitable wired and/or wireless network(s) including, for example, one or more data buses, one or more Local Area Networks (LANs), one or more wireless LANs, one or more cellular networks, the Internet, etc. As used herein, the phrase "in communication," including variances thereof, encompasses direct communication and/or indirect communication through one or more intermediary components and does not require direct physical (e.g., wired) communication and/or constant communication, but rather additionally includes selective communication at periodic or aperiodic intervals, as well as one-time events.
[0024] In the illustrated example of FIG. 1, an online social messaging service operates and/or hosts the message hosting server 104 that responds to requests for social media messages by the AME server 108. Additionally or alternatively, the message hosting server 104 may be in communication with a geographically separate messages database (e.g., a server of a third-party contracted by the online social messaging service) that hosts the social media messages. In such examples, the message hosting server 104 retrieves messages from the separate messages database to serve the messages to the requesting AME server 108.
Alternatively, the separate messages database may be provided with a server to serve the hosted messages directly to the requesting AME server 108. In addition, for simplicity, only one message hosting server 104 is shown in FIG. 1, although multiple message hosting servers are likely to be present.
Alternatively, the separate messages database may be provided with a server to serve the hosted messages directly to the requesting AME server 108. In addition, for simplicity, only one message hosting server 104 is shown in FIG. 1, although multiple message hosting servers are likely to be present.
[0025] In the illustrated example, a user signs into an online social media service with a user identifier (e.g., an example user identifier 112) in order to read and/or convey (or send) social media messages. The example user identifier 112 is then associated with the activities for the user. For example, the user identifier 112 may be displayed (or presented) along with the social media message.
[0026] In the illustrated example, when a message sender posts or sends a social media message 114, that social media message 114 is sent to the message hosting server 104. The example message hosting server 104 hosts asset-regarding social media messages 114A and non-asset regarding social media messages 114B. In the illustrated example, asset-regarding social media messages 114A include reference(s) (e.g., text) at least partially directed to an asset of interest and also include characteristics indicating exposure to the asset of interest. For example, an asset of interest may be "The Daily Show with Jon Stewart." In such instances, an asset-regarding social media message 114A may include the text "Jon Stewart is really funny on The Daily Show right now!" and may include a message timestamp 116 indicating that the as regarding social media message 114A was posted by the message sender during broadcast of the asset of interest.
[0027] In contrast, a non-asset regarding social media message 114B does not include reference to an asset of interest and/or does not include a characteristic indicating exposure to an asset of interest. For example, a non-asset regarding social media message 114B may include reference to an asset of interest (e.g., the text "Just ran into Jon Stewart from The Daily Show at my favorite pizza parlor!"), but the message may not have been posted by the message sender during broadcast times associated with the television show. In the illustrated example, the message hosting server 104 serves asset-regarding social media messages 114A
and non-asset regarding social media messages 114B to the AME server 108 in the same manner.
For example, the message hosting server 104 processes a request for a social media message 114 similarly regardless of whether the social media message 114 is an asset-regarding social media message 114A or a non-asset regarding social media message 114B.
and non-asset regarding social media messages 114B to the AME server 108 in the same manner.
For example, the message hosting server 104 processes a request for a social media message 114 similarly regardless of whether the social media message 114 is an asset-regarding social media message 114A or a non-asset regarding social media message 114B.
[0028] In the illustrated example of FIG. 1, the asset proprietor 106 distributes and/or provides media events, products and/or services to large numbers of subscribers. In exchange for the provision of the asset, the subscribers register with the asset proprietor 106. As part of this registration, the subscribers provide detailed user demographic information.
Examples of such asset proprietors 106 include retailers and/or service providers such as Amazon.com, eBay, Pandora, Hulu, etc.
Examples of such asset proprietors 106 include retailers and/or service providers such as Amazon.com, eBay, Pandora, Hulu, etc.
[0029] The example AME server 108 of the illustrated example operates to impute demographic information of a known first group of people onto an unknown second group of people. For example, to infer demographics for users of social media who send social media messages regarding an asset, the AME server 108 may use demographics developed for a panel (e.g., a television panel, a loyalty card panel, etc.). In some examples, the AME server 108 periodically and/or aperiodically queries the message hosting server 104 for social media messages using a keywords list. Returned social media messages 115 by the message hosting server 104 are processed to determine whether they correspond to an asset of interest such as a media event, a product and/or a service. In the example of FIG. 1, the social media messages 114 and 115 are the same message at two different points in time. Message 114 is the message prior to being served to the AME server 108 (e.g., while hosted at the message hosting server 104). Message 115 is the message after serving. The example AME server 108 identifies the user identifier 112 associated with the returned social media message 115 and tags the user identifier 112 with known demographic information for the asset.
[0030] In the illustrated example, to tag the user identifier 112 with known demographic information for an asset of interest, the AME 102 of the illustrated example also collects and/or has access to demographic information for the asset(s) of interest. For example, the AME 102 may collect media identifying information indicative of particular media being presented in a media exposure environment (e.g., a television room, a family room, a living room, a bar, a restaurant, a store, a cafeteria, etc.) by a media presentation device such as a television and store the demographic information. The AME 102 may then correlate data collected from a plurality of panelist sites with the demographics of the panelists at those sites. For example, for each panelist site wherein a first piece of media is detected in the monitored environment at a first time, media identifying information for the first piece of media is correlated with presence information detected in the environment at the first time. The data and/or results from multiple panelist sites are combined and/or analyzed to provide demographic information representative of exposure of a population as a whole to the first piece of media.
[0031] In the illustrated example of FIG. 1, the AME 102 includes an example reference database 118 to identify assets of interest and to tag user identifiers 112 associated with asset-regarding social media messages 114A with known demographic information (e.g., a set of different demographic buckets corresponding to a known audience composition) of the asset included in the reference database 118. As described in detail below, the example reference database 118 may include, for example, an asset of interest identifier 120 (e.g., "The Daily Show with Jon Stewart"), one or more rule(s) 122 associated with the asset (e.g., airs between 10:00 p.m. Central Standard Time (CST) and 10:30 p.m. CST Monday through Thursday), known demographic information 124 about the asset (e.g., segments or market breaks such as 70% male age 20-29, 20% female age 20-29, 6% male less than age 20, 4% female less than age 20), and a demographics tag 126 associated with the demographic segments (e.g., tag A).
The example reference database 118 may include a volatile memory (e.g., a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory).
The example reference database 118 may include one or more double data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The example reference database 118 may additionally or alternatively include one or more mass storage devices such as hard drive disk(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the reference database 118 is illustrated as a single database, the reference database 118 may be implemented by any number and/or type(s) of databases.
The example reference database 118 may include a volatile memory (e.g., a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory).
The example reference database 118 may include one or more double data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The example reference database 118 may additionally or alternatively include one or more mass storage devices such as hard drive disk(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the reference database 118 is illustrated as a single database, the reference database 118 may be implemented by any number and/or type(s) of databases.
[0032] In some examples, the AME 102 uses demographics from a consumer purchase panel (e.g., Nielsen's HomescanTM panel, a loyalty card panel, Nielsen television panel, Nielsen online panel, Nielsen radio panel, etc.). In such panelist-based systems (e.g., television panels, consumer purchase panels, etc.), user demographic information is obtained from a user when, for example, the user joins and/or registers for the panel (e.g., consents to being monitored into a panel). The user demographic information (e.g., race, age or age range, gender, income, education level, etc.) may be obtained from the user, for example, via a telephone interview, an in-person interview, by having the user complete a survey (e.g., an online survey), etc. In some examples, the AME 102 uses the collected demographic information from the enrolling people (e.g., panelists) so that subsequent correlations may be made between asset exposure to those panelists and different demographic markets. For example, the AME 102 may monitor those panel members to determine assets (e.g., media events, products, services, etc.) exposed to those panel manners. The AME 102 then compiles the collected data into statistical reports accurately identifying different demographic buckets of persons exposed to the asset.
[0033] In some examples, the AME 102 may collect and/or obtain the asset demographic information 124 from the asset proprietor 106. In some such examples, the AME
102 may leverage the existing databases of the asset proprietor 106 to collect more extensive asset demographic information 124 and/or user data for associating with users of social media.
Collecting user demographic information associated with registered panelists and/or users of the asset proprietor 106 enables the AME 102 to extend or supplement their panel data with substantially reliable demographic information from external sources (e.g., the asset proprietor 106), thereby extending the coverage, accuracy, and/or completeness of their known demographic information for assets. The use of demographic information from disparate data sources (e.g., high-quality demographic information from the panel(s) of an audience measurement entity and/or registered user data of the asset proprietor 106) results in improved prediction of the demographics associated with a particular user of social media by the AME
102.
102 may leverage the existing databases of the asset proprietor 106 to collect more extensive asset demographic information 124 and/or user data for associating with users of social media.
Collecting user demographic information associated with registered panelists and/or users of the asset proprietor 106 enables the AME 102 to extend or supplement their panel data with substantially reliable demographic information from external sources (e.g., the asset proprietor 106), thereby extending the coverage, accuracy, and/or completeness of their known demographic information for assets. The use of demographic information from disparate data sources (e.g., high-quality demographic information from the panel(s) of an audience measurement entity and/or registered user data of the asset proprietor 106) results in improved prediction of the demographics associated with a particular user of social media by the AME
102.
[0034] In the illustrated example, the AME server 108 generates user profiles 128 for users using the demographic information associated with the user via their user identifier 112. For example, the AME server 108 may periodically and/or aperiodically identify the demographics tags 126 associated with the user identifier 112 and perform statistical analysis such as Bayesian analysis of the corresponding demographics. In some examples, the AME server 108 performs statistical analysis of the variations within the demographics to generate the user profile 128. In some examples, the AME server 108 combines the demographic composition of multiple events for a same user (e.g., one or more exposures to one or more television shows and/or one or more product purchases) to more accurately determine the demographics for the user.
For example, combining the likelihoods that the user fits into different demographic categories based on different audience compositions from two or more events results in a combined set of likelihoods for the user's demographics. The demographic categories (e.g., segments or market breaks) with the highest likelihood are identified as the demographics for the user. Larger numbers of events/audience participation that can be associated with a given user over time (e.g., via the user identifier 112) achieve better accuracy of the demographics imputations. The AME 102 of the illustrated example may provide the generated profiles 128 to companies and/or individuals that produce the asset.
For example, combining the likelihoods that the user fits into different demographic categories based on different audience compositions from two or more events results in a combined set of likelihoods for the user's demographics. The demographic categories (e.g., segments or market breaks) with the highest likelihood are identified as the demographics for the user. Larger numbers of events/audience participation that can be associated with a given user over time (e.g., via the user identifier 112) achieve better accuracy of the demographics imputations. The AME 102 of the illustrated example may provide the generated profiles 128 to companies and/or individuals that produce the asset.
[0035] FIG. 2 illustrates an example data table 200 that may be stored by the example reference database 118 of the example AME 102 of FIG. 1 to facilitate associating users of social media services with demographic information. In the illustrated example of FIG. 2, the data table 200 associates an asset identifier 120 with one or more rule(s) 122, asset demographic information 124 and a demographics tag 126. The association is accomplished by putting data in the appropriate column of the same row of the data table 200. In the illustrated example, the asset identifier 120 identifies an asset of interest such as a television program (e.g., the asset (The Daily Show with Jon Stewart) of row 202), a book (e.g., the asset (Twilight (book)) of row 204), a product (e.g., the asset (necklace) of row 206), etc. The example one or more rule(s) 122 include one or more values and/or data corresponding to criteria associated with the corresponding asset identifier 120. In some examples, the one or more rule(s) 122 include time blocks during which a television show airs. For example, in row 202, the one or more rule(s) 122 associated with the asset (The Daily Show with Jon Stewart) indicate that the asset (The Daily Show with Jon Stewart) is broadcast Monday through Thursday and between 10:00 p.m.
Central Standard Time (CST) and 10:30 p.m. (CST). In some examples, the one or more rule(s) 122 include vendors and/or merchants that sell products and/or provide media (e.g., assets of interest) included in the reference database 118. For example, in row 208, the one or more rule(s) 122 associated with the asset (End of the World (movie)) indicate that the asset (End of the World (movie)) may be accessed (e.g., purchased, streamed, etc.) from Amazon.com and/or through iTunes .
Central Standard Time (CST) and 10:30 p.m. (CST). In some examples, the one or more rule(s) 122 include vendors and/or merchants that sell products and/or provide media (e.g., assets of interest) included in the reference database 118. For example, in row 208, the one or more rule(s) 122 associated with the asset (End of the World (movie)) indicate that the asset (End of the World (movie)) may be accessed (e.g., purchased, streamed, etc.) from Amazon.com and/or through iTunes .
[0036] As discussed above, demographic information for an asset may be collected and/or leveraged by the AME 102. The data table 200 of FIG. 2 includes the asset demographic information 124 (e.g., demographic segments, market breaks, etc.) associated with the corresponding asset. The asset demographic information 124 may include data and/or value(s) indicative of one or more of an age or age range (e.g., 20-29), gender, education level, etc.
associated with the asset identifier 120. In some examples, the AME 102 collects and/or has access to demographic information for the asset(s) of interest. For example, the AME 102 may correlate data collected from a plurality of monitored panelist sites with the demographics of the panelists at those sites and/or user demographic information associated with registered panelists and/or users of the asset proprietor 106. For example, in row 206, the asset demographic information 124 associated with the asset (necklace) indicates that a purchaser of the asset (necklace) has a 70% likelihood of being a female and a 30% likelihood of being a male.
Further, in row 210, the asset demographic information 124 associated with the asset (End of the World (song)) indicates that a user who accesses (e.g., purchases, streams, etc.) the asset (End of the World (song)) has a 70% likelihood of being between the ages of 20-29, a 20% likelihood of being less than 20 years of age, and 10% likelihood of being between the ages of 30-39. In the illustrated example of FIG. 2, the demographics tag 126 corresponds to the asset demographic information 124 and may be used to refer to the demographic segments of the associated asset identifier 120. For example, in row 206, the demographics tag 126 associated with the asset (necklace) indicates that the demographic segments of the asset (necklace) may be referred to by a tag (Tag C). One or more demographic tags (e.g., one or more values or data) may apply to any given asset. Thus, the demographics tag 126 may be populated with one or more tags.
associated with the asset identifier 120. In some examples, the AME 102 collects and/or has access to demographic information for the asset(s) of interest. For example, the AME 102 may correlate data collected from a plurality of monitored panelist sites with the demographics of the panelists at those sites and/or user demographic information associated with registered panelists and/or users of the asset proprietor 106. For example, in row 206, the asset demographic information 124 associated with the asset (necklace) indicates that a purchaser of the asset (necklace) has a 70% likelihood of being a female and a 30% likelihood of being a male.
Further, in row 210, the asset demographic information 124 associated with the asset (End of the World (song)) indicates that a user who accesses (e.g., purchases, streams, etc.) the asset (End of the World (song)) has a 70% likelihood of being between the ages of 20-29, a 20% likelihood of being less than 20 years of age, and 10% likelihood of being between the ages of 30-39. In the illustrated example of FIG. 2, the demographics tag 126 corresponds to the asset demographic information 124 and may be used to refer to the demographic segments of the associated asset identifier 120. For example, in row 206, the demographics tag 126 associated with the asset (necklace) indicates that the demographic segments of the asset (necklace) may be referred to by a tag (Tag C). One or more demographic tags (e.g., one or more values or data) may apply to any given asset. Thus, the demographics tag 126 may be populated with one or more tags.
[0037] FIG. 3 is a block diagram of an example implementation of the audience measurement entity (AME) server 108 of FIG. 1 that may facilitate estimating demographics of users employing social media. The example AME server 108 of the illustrated example includes an example tagged identifier logger 302, an example tagged identifiers database 304, an example profile generator 306, an example profiles database 314, an example time stamper 316, an example data storer 318 and an example reporter 320.
[0038] In the illustrated example of FIG. 3, the AME server 108 includes the example tagged identifier logger 302 to log user identifiers associated with social media messages posted by users regarding assets of interest. As described in detail below, the example tagged identifier logger 302 tags a user identifier 112 associated with the asset-regarding social media message 114a with known demographic information associated with the asset. For example, the tagged identifier logger 302 may query message hosting servers (e.g., the message hosting server 104 of FIG. 1) for social media messages 114 associated with an asset identifier 120.
The example tagged identifier logger 302 processes the returned social media message 115 and when the example tagged identifier logger 302 of the illustrated example determines that the returned social media message 115 includes reference to an asset of interest and includes characteristics indicating exposure to the asset of interest (e.g., the returned social media message 115 is an asset-regarding social media message 114A), the tagged identifier logger 302 uses the example reference database 118 of FIG. 1 to identify demographic information associated with the identified asset. The example tagged identifier logger 302 of FIG. 3 identifies the user identifier 112 associated with the asset-regarding social media message 114A and tags (e.g., associates) the user identifier 112 with the asset demographic information 124 retrieved from the reference database 118.
The example tagged identifier logger 302 processes the returned social media message 115 and when the example tagged identifier logger 302 of the illustrated example determines that the returned social media message 115 includes reference to an asset of interest and includes characteristics indicating exposure to the asset of interest (e.g., the returned social media message 115 is an asset-regarding social media message 114A), the tagged identifier logger 302 uses the example reference database 118 of FIG. 1 to identify demographic information associated with the identified asset. The example tagged identifier logger 302 of FIG. 3 identifies the user identifier 112 associated with the asset-regarding social media message 114A and tags (e.g., associates) the user identifier 112 with the asset demographic information 124 retrieved from the reference database 118.
[0039] In the illustrated example of FIG. 3, the tagged identifier logger 302 stores the record of the tagged user identifier in the example tagged identifiers database 304.
The tagged identifiers database 304 may include a volatile memory (e.g., a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory).
The tagged identifiers database 304 may include one or more double data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The tagged identifiers database 304 may additionally or alternatively include one or more mass storage devices such as hard drive disk(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the tagged identifiers database 304 is illustrated as a single database, the tagged identifiers database 304 may be implemented by any number and/or type(s) of databases.
The tagged identifiers database 304 may include a volatile memory (e.g., a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory).
The tagged identifiers database 304 may include one or more double data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR (mDDR), etc. The tagged identifiers database 304 may additionally or alternatively include one or more mass storage devices such as hard drive disk(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the tagged identifiers database 304 is illustrated as a single database, the tagged identifiers database 304 may be implemented by any number and/or type(s) of databases.
[0040] In the illustrated example of FIG. 3, the AME server 108 includes the example profile generator 306 to generate user profiles 128 including estimated demographics for the corresponding users who post social media messages regarding assets of interest (e.g., the example asset-regarding social media messages 114A). For example, the profile generator 306 may periodically and/or aperiodically process a user identifier 112 included in the tagged identifiers database 304 and perform statistical analysis of the asset demographic information 124 tagged to the user identifier 112. Using the results of the analysis, the example profile generator 306 estimates demographics for the user associated with the user identifier 112.
[0041] In some examples, the profile generator 306 generates user profiles 128 when requested. For example, the profile generator 306 may receive a request from, for example, the example reporter 320 to generate a user profile 128 for a certain user. In some examples, the profile generator 306 generates user profiles 128 aperiodically (e.g., when the profile generator 306 detects a change in information stored in the example tagged identifiers database 304). For example, when the tagged identifier logger 302 records a tagged identifier in the tagged identifiers database 304, the profile generator 306 may detect the new record and process the new record. For example, the profile generator 306 may update a previously generated user profile 128 associated with the user identifier 112 of the new record. In some examples, the profile generator 306 periodically generates a user profile 128. For example, the profile generator 306 may generate a user profile 128 for the one or more user identifiers 112 included in the tagged identifiers database 304 every 24 hours. The profile generator 306 of the illustrated example includes an example demographics filterer 308, an example demographics analyzer 310 and an example estimator 312.
[0042] In the illustrated example of FIG. 3, the profile generator 306 includes the example demographics filterer 308 to identify demographic information associated with a specific user identifier. For example, the demographics filterer 308 may parse the tagged identifiers database 304 and identify the different demographics tagged to the user identifier 112.
In some examples, the demographics filterer 308 sorts and/or combines the records in the tagged identifiers database 304 based on the distinct user identifiers 112. For example, the demographic filterer 308 may link together one or more demographics tags 126 associated with the user identifier 112. In some examples, the demographics filterer 308 may aggregate demographic information for two or more user identifiers 112 included in the tagged identifiers database 304.
For example, the demographics filterer 308 may associate different user identifiers 112 with the same user. For example, the demographics filterer 308 may access a data structure such as a lookup table, a file, a database, a list, etc. that cross-references based on information received from, for example, one or more asset proprietors 106. For instance, a user may register with a first online social media service using a first user identifier (e.g., "@JohnDoe") and register with a second online social media service using a second user identifier (e.g., "Johnny_Doe"). In some examples, the demographics filterer 308 may identify two or more user identifiers that are sufficiently the same (e.g., the user identifiers "@Jane_Doe," "Jane Doe" and "Doe, Jane") and associate the different user identifiers with the same user. In some such examples, the demographics filterer 308 combines the demographic information tagged to the first user identifier and the second user identifier to generate the profile for the user.
In some examples, the demographics filterer 308 sorts and/or combines the records in the tagged identifiers database 304 based on the distinct user identifiers 112. For example, the demographic filterer 308 may link together one or more demographics tags 126 associated with the user identifier 112. In some examples, the demographics filterer 308 may aggregate demographic information for two or more user identifiers 112 included in the tagged identifiers database 304.
For example, the demographics filterer 308 may associate different user identifiers 112 with the same user. For example, the demographics filterer 308 may access a data structure such as a lookup table, a file, a database, a list, etc. that cross-references based on information received from, for example, one or more asset proprietors 106. For instance, a user may register with a first online social media service using a first user identifier (e.g., "@JohnDoe") and register with a second online social media service using a second user identifier (e.g., "Johnny_Doe"). In some examples, the demographics filterer 308 may identify two or more user identifiers that are sufficiently the same (e.g., the user identifiers "@Jane_Doe," "Jane Doe" and "Doe, Jane") and associate the different user identifiers with the same user. In some such examples, the demographics filterer 308 combines the demographic information tagged to the first user identifier and the second user identifier to generate the profile for the user.
[0043] In the illustrated example of FIG. 3, the profile generator 306 includes the example demographics analyzer 310 to analyze the demographic information identified by the demographics tags 126 and determine the likelihoods that the user fits into different demographic buckets. In some examples, the demographics analyzer 310 performs statistical analysis of the variations within the identified demographics associated with the user. For example, the demographics analyzer 310 may apply Bayesian analysis or principal component analysis to the different demographics to develop the likelihoods. In some such examples, the demographics analyzer 310 applies statistical methods (e.g., Bayesian analysis) to the different demographic pools associated with the user to obtain a more precise demographic estimation of that user. For example, combining the likelihoods that the user fits into different demographic categories based on different audience compositions from two or more tagged identifier records (e.g., one or more exposures to one or more television programs and/or one or more product purchases) results in a combined set of likelihoods for the user's demographics. In some examples, the demographics analyzer 310 associates weights with the different demographic information tagged to the user.
However, the example demographics analyzer 310 may use other statistical procedures (e.g., principal component analysis) to determine the likelihoods that the user fits into different demographic buckets.
However, the example demographics analyzer 310 may use other statistical procedures (e.g., principal component analysis) to determine the likelihoods that the user fits into different demographic buckets.
[0044] In the illustrated example of FIG. 3, the profile generator 306 includes the example estimator 312 to estimate the demographics for the user based on the results of the analysis performed by the example demographics analyzer 310. For example, the estimator 312 may identify the demographic category (or categories) with the highest likelihood and associate the corresponding demographic category with the user. In general, larger numbers of tagged identifier records (and corresponding demographic information) associated with a given user over time increases the accuracy of the demographics imputations. In the illustrated example of FIG. 3, the profile generator 306 uses the results of the estimator 312 to generate the user profile 128.
[0045] In the illustrated example of FIG. 3, the profile generator 306 stores the generated user profile 128 in the example profiles database 314. The profiles database 314 may include a volatile memory (e.g., a Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM, etc.) and/or a non-volatile memory (e.g., flash memory). The profiles database 314 may include one or more double data rate (DDR) memories, such as DDR, DDR2, DDR3, mobile DDR
(mDDR), etc. The profiles database 314 may additionally or alternatively include one or more mass storage devices such as hard drive disk(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the profiles database 314 is illustrated as a single database, the profiles database 314 may be implemented by any number and/or type(s) of databases.
(mDDR), etc. The profiles database 314 may additionally or alternatively include one or more mass storage devices such as hard drive disk(s), compact disk drive(s), digital versatile disk drive(s), etc. While in the illustrated example the profiles database 314 is illustrated as a single database, the profiles database 314 may be implemented by any number and/or type(s) of databases.
[0046] The example time stamper 316 of FIG. 3 includes a clock and a calendar. The example time stamper 316 associates a time period (e.g., 1:00 a.m. Central Standard Time (CST) to 1:01 a.m. (CST) and/or a date (e.g., January 1, 2013) with each generated user profile 128 by, for example, appending the period of time and/or the date information to an end of the data in the user profile 128.
[0047] In the illustrated example of FIG. 3, the AME server 108 includes the example data storer 318 to store tagged identifier records logged by the example tagged identifier logger 302 and/or user profiles 128 generated by the example profile generator 306.
[0048] In the illustrated example, the reporter 320 generates reports based on the generated user profiles. In some examples, the reporter 320 generates reports for a certain user. For example, the reporter 320 may receive a query for a certain user from, for example, the AME
102. In some such examples, the reporter 320 causes the profile generator 306 to generate a report for the specified user. In some examples, the reports are presented to the companies and/or individuals that produce the different assets. The reports may identify different aspects of asset exposure such as which age range(s) and/or genders are more likely to send social media messages when exposed to an asset. For example, the reports may determine whether those who send social media messages about a media event (e.g., a television program) in real-time are the same demographic distribution as the viewers of the media event. Reports may also show that the social media users are young for a first media event but relatively older for a second media event.
102. In some such examples, the reporter 320 causes the profile generator 306 to generate a report for the specified user. In some examples, the reports are presented to the companies and/or individuals that produce the different assets. The reports may identify different aspects of asset exposure such as which age range(s) and/or genders are more likely to send social media messages when exposed to an asset. For example, the reports may determine whether those who send social media messages about a media event (e.g., a television program) in real-time are the same demographic distribution as the viewers of the media event. Reports may also show that the social media users are young for a first media event but relatively older for a second media event.
[0049] While an example manner of implementing the audience measurement entity (AME) server 108 of FIG. 1 is illustrated in FIG. 3, one or more of the elements, processes and/or devices illustrated in FIG. 3 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way. Further, the example tagged identifier logger 302, the example tagged identifiers database 304, the example profile generator 306, the example demographics filterer 308, the example demographics analyzer 310, the example estimator 312, the example profiles database 314, the example time stamper 316, the example data storer 318, the example reporter 320 and/or, more generally, the example AME server 108 of FIG. 1 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware. Thus, for example, any of the example tagged identifier logger 302, the example tagged identifiers database 304, the example profile generator 306, the example demographics filterer 308, the example demographics analyzer 310, the example estimator 312, the example profiles database 314, the example time stamper 316, the example data storer 318, the example reporter 320 and/or, more generally, the example AME server 108 could be implemented by one or more analog or digital circuit(s), logic circuits, programmable processor(s), application specific integrated circuit(s) (ASIC(s)), programmable logic device(s) (PLD(s)) and/or field programmable logic device(s) (FPLD(s)). When reading any of the apparatus or system claims of this patent to cover a purely software and/or firmware implementation, at least one of the example tagged identifier logger 302, the example tagged identifiers database 304, the example profile generator 306, the example demographics filterer 308, the example demographics analyzer 310, the example estimator 312, the example profiles database 314, the example time stamper 316, the example data storer 318 and/or the example reporter 320 is/are hereby expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. storing the software and/or firmware. Further still, the example AME server 108 of FIG. 1 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated in FIG. 3, and/or may include more than one of any or all of the illustrated elements, processes and devices.
[0050] FIG. 4 is a block diagram of an example implementation of the tagged identifier logger 302 of FIG. 3 that may facilitate tagging a user identifier associated with a social media message posted by a user regarding an asset of interest with known demographic information associated with the asset. The example tagged identifier logger 302 of the illustrated example includes an example message retriever 402, an example message analyzer 404, an example timestamp retriever 406, an example rules checker 408 and an example identifier tagger 410.
[0051] In the illustrated example of FIG. 4, the tagged identifier logger 302 includes the example message retriever 402 to retrieve social media messages (e.g., the example social media messages 114, 115 of FIG. 1) from message hosting servers (e.g., the example message hosting server 104 of FIG. 1). For example, the message retriever 402 may query the message hosting server 104 for a social media message 114 at periodic intervals (e.g., every 24 hours, every Monday, etc.), aperiodic intervals (e.g., when requested), and/or as a one-time event. In the illustrated example of FIG. 4, the message retriever 402 uses an example keywords list 412 including one or more keyword(s) when querying the message hosting server 104.
As used herein, the phrase "keyword" includes words and/or phrases that have a dictionary definition and/or correspond to a name and/or correspond to colloquiums that may not have an accepted dictionary definition. Further, although examples disclosed herein are described in connection with a list, many other methods of implementing the keywords list 412 may alternatively be used. For example, disclosed techniques may also be used in connection with a table (e.g., a lookup table), a file, a database, etc.
As used herein, the phrase "keyword" includes words and/or phrases that have a dictionary definition and/or correspond to a name and/or correspond to colloquiums that may not have an accepted dictionary definition. Further, although examples disclosed herein are described in connection with a list, many other methods of implementing the keywords list 412 may alternatively be used. For example, disclosed techniques may also be used in connection with a table (e.g., a lookup table), a file, a database, etc.
[0052] In the illustrated example, the keywords list 412 includes example keywords 412A, 412B, 412C, 412D. When the example message retriever 402 of the illustrated example queries the message hosting server 104 for social media messages, the message retriever 402 requests only those social media messages 114 that include the keywords in the keywords list 412. In this manner, the example message retriever 402 reduces (e.g., minimizes) the number of social media messages 115 that are returned by the message hosting server 104 that were not posted by a user associated with an asset of interest identifier 120. For example, rather than querying the message hosting server 104 for social media messages 114 that include a television program name (E.R.), which may return social media messages 115 posted by users waiting in an emergency room, the example message retriever 402 of the illustrated example may also include the keywords "I'm watching" as well as a media provider that may enable watching and/or distributes the television program (e.g., @Hulu). In some examples, the message retriever 402 requests one or more social media messages 114 from the message hosting server 104 and then uses the keywords list 412 to filter the social media messages 115 to reduce the set of social media messages 115 to subsequently process. For example, the message retriever 402 may request all social media messages 114 posted to the message hosting server 104 within a time period (e.g., 5:00 p.m.
Central Standard Time (CST) to 5:59 p.m. (CST)) and/or a date or date range.
The example message retriever 402 may subsequently filter the social media messages 115 using the keywords list 412. In some examples, the message retriever 402 uses one or more keywords when retrieving social media messages. For example, the message retriever 402 may query the message hosting server 104 for social media messages 114 using a first keyword (e.g., an asset identifier 120 such as E.R.) and subsequently filter the returned social media messages 115 using a second keyword (e.g., "I'm watching via @Hulu"). The filtering may be performed using any combination of Boolean operation (e.g., AND, OR, etc.).
Central Standard Time (CST) to 5:59 p.m. (CST)) and/or a date or date range.
The example message retriever 402 may subsequently filter the social media messages 115 using the keywords list 412. In some examples, the message retriever 402 uses one or more keywords when retrieving social media messages. For example, the message retriever 402 may query the message hosting server 104 for social media messages 114 using a first keyword (e.g., an asset identifier 120 such as E.R.) and subsequently filter the returned social media messages 115 using a second keyword (e.g., "I'm watching via @Hulu"). The filtering may be performed using any combination of Boolean operation (e.g., AND, OR, etc.).
[0053] While querying the message hosting server 104 using the keywords phrase 412D may reduce the number of returned social media messages 115 to those regarding an asset (e.g., a television program), the television program included in the social media messages 115 may not be regarding a television program of interest. In the illustrated example of FIG. 4, the tagged identifier logger 302 includes the example message analyzer 404 to determine whether the returned social media message 115 includes an asset of interest. For example, the message analyzer 404 may compare the text of the social media message 115 to the asset identifiers 120 listed in the reference database 118. In some examples, if the returned social media message 115 does not include an asset of interest (e.g., the example non-asset regarding message 114b), the message analyzer 404 discards the social media message (e.g., the messages 114b, 115).
[0054] In the illustrated example of FIG. 4, the tagged identifier logger 302 includes the example timestamp retriever 406 to obtain a timestamp corresponding to when the returned social media message 115 was posted (e.g., when the message was sent by a user, when the status was updated, etc.). In some examples, the timestamp retriever 406 parses the social media message 115 to identify the message timestamp 116. In some examples, the timestamp retriever 406 may request the corresponding message timestamp from the message hosting server 104. As described in detail below, in some examples, the message timestamp 116 may be used to determine whether the returned social media message 115 was posted contemporaneous and/or near contemporaneous to an asset of interest (e.g., a media event).
[0055] In the illustrated example of FIG. 4, the tagged identifier logger 302 includes the example rules checker 408 to ensure only statements indicating an appropriate exposure to an asset are reflected in the social media message statement. The example rules checker 408 functions to increase the probability of the example AME server 108 properly imputing demographics to a social media service user. In some examples, the rules checker 408 functions as a false positive checker. In the illustrated example, the rules checker 408 compares characteristics of the returned social media message 115 to one or more rule(s) 122 associated with the asset identifier 120 identified in the social media message 115. For example, the rules checker 408 may determine whether text of the social media message 115 includes a known vendor or merchant that supplies (e.g., sells) the identified asset (e.g., a product of interest). In some examples, the rule checker 408 compares the message timestamp 116 retrieved by the timestamp retriever 406 to determine whether the message timestamp 116 is sufficiently near the broadcast time(s) of a television program to safely conclude exposure to the television program occurred to thereby link the user via the user identifier 112 to the demographics of the television program audience. In some examples, the rules checker 408 may use a time window based on the broadcast times. For example, the rules checker 408 may perform a time-series analysis of message timestamps to determine a time-lag between real-time broadcast of a television program and when messages related to the television program are posted by users. The example rules checker 408 of the illustrated example uses the time-lag to determine whether the social media message 115 was sent in response to a user viewing the television program (e.g., during or shortly after (e.g., within fifteen minutes of) broadcast of the television program).
[0056] In the illustrated example of FIG. 4, the tagged identifier logger 302 includes the example identifier tagger 410 to associate known demographic information of the asset of interest to the user. In some examples, the identifier tagger 410 parses the asset-regarding social media message 114A and identifies the user identifier 112 associated with the message 114A.
The example identifier tagger 410 of the illustrated example then tags the user identifier 112 with asset demographic information 124 associated with the asset of interest. For example, the identifier tagger 410 may retrieve the asset demographic information 124 and/or the demographics tag 126 associated with the identified asset identifier 120 from the example reference database 118 and associate the asset demographic information 124 and/or the demographics tag 126 with the user identifier 112. In some examples, the identifier tagger 410 may include additional information along with the tagged identifier such as text included in the asset-regarding social media message 114A and/or an identifier (e.g., a message identifier) to access the message 114A at a subsequent time, which keyword(s) from the keywords list 412 were used by the message retriever 402 to retrieve the asset-regarding social media message 114A, the asset of interest identifier 120 identified by the message analyzer 404, the message timestamp 116 associated with the asset-regarding social media message 114A, etc.
The example identifier tagger 410 of the illustrated example then tags the user identifier 112 with asset demographic information 124 associated with the asset of interest. For example, the identifier tagger 410 may retrieve the asset demographic information 124 and/or the demographics tag 126 associated with the identified asset identifier 120 from the example reference database 118 and associate the asset demographic information 124 and/or the demographics tag 126 with the user identifier 112. In some examples, the identifier tagger 410 may include additional information along with the tagged identifier such as text included in the asset-regarding social media message 114A and/or an identifier (e.g., a message identifier) to access the message 114A at a subsequent time, which keyword(s) from the keywords list 412 were used by the message retriever 402 to retrieve the asset-regarding social media message 114A, the asset of interest identifier 120 identified by the message analyzer 404, the message timestamp 116 associated with the asset-regarding social media message 114A, etc.
[0057] While an example manner of implementing the tagged identifier logger 302 of FIG. 3 is illustrated in FIG. 4, one or more of the elements, processes and/or devices illustrated in FIG.
4 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way. Further, the example message retriever 402, the example message analyzer 404, the example timestamp retriever 406, the example rules checker 408, the example identifier tagger 410 and/or, more generally, the example tagged identifier logger 302 of FIG. 3 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware. Thus, for example, any of the example message retriever 402, the example message analyzer 404, the example timestamp retriever 406, the example rules checker 408, the example identifier tagger 410 and/or, more generally, the example tagged identifier logger 302 could be implemented by one or more analog or digital circuit(s), logic circuits, programmable processor(s), application specific integrated circuit(s) (ASIC(s)), programmable logic device(s) (PLD(s)) and/or field programmable logic device(s) (FPLD(s)). When reading any of the apparatus or system claims of this patent to cover a purely software and/or firmware implementation, at least one of the example message retriever 402, the example message analyzer 404, the example timestamp retriever 406, the example rules checker 408 and/or the example identifier tagger 410 is/are hereby expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. storing the software and/or firmware.
Further still, the example tagged identifier logger 302 of FIG. 3 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated in FIG. 4, and/or may include more than one of any or all of the illustrated elements, processes and devices.
4 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way. Further, the example message retriever 402, the example message analyzer 404, the example timestamp retriever 406, the example rules checker 408, the example identifier tagger 410 and/or, more generally, the example tagged identifier logger 302 of FIG. 3 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware. Thus, for example, any of the example message retriever 402, the example message analyzer 404, the example timestamp retriever 406, the example rules checker 408, the example identifier tagger 410 and/or, more generally, the example tagged identifier logger 302 could be implemented by one or more analog or digital circuit(s), logic circuits, programmable processor(s), application specific integrated circuit(s) (ASIC(s)), programmable logic device(s) (PLD(s)) and/or field programmable logic device(s) (FPLD(s)). When reading any of the apparatus or system claims of this patent to cover a purely software and/or firmware implementation, at least one of the example message retriever 402, the example message analyzer 404, the example timestamp retriever 406, the example rules checker 408 and/or the example identifier tagger 410 is/are hereby expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. storing the software and/or firmware.
Further still, the example tagged identifier logger 302 of FIG. 3 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated in FIG. 4, and/or may include more than one of any or all of the illustrated elements, processes and devices.
[0058] FIG. 5 illustrates an example data table 500 storing data representing tagged identifiers that may be collected by the example AME server 108 of FIGS. 1, 3 and/or 4. In the illustrated example of FIG. 5, the data table 500 identifies a user identifier 112, a demographics tag 126, a message identifier 502, message keywords information 504, an asset identifier 120 and a message timestamp 116. In the illustrated example, the AME server 108 extracts the user identifier 112 from the asset-regarding social media message 114A when the message 114A
corresponds to an asset of interest (e.g., includes a reference to the asset identifier 120). For example, in row 514, the user identifier 112 indicates that a user associated with the user identifier 112 (@user3) posted the corresponding asset-regarding social media message 114A.
Further, the AME server 108 identifies demographic information associated with the asset identifier 120 (necklace) and tags the user identifier 112 (@user3) with the corresponding demographics tag 126 (Tag C). In the illustrated example, the AME server 108 also stores additional information from the asset-regarding social media message 114A in the tagged identifier record. For example, in row 510, the tagged identifier logger 302 associates the asset-regarding social media message 114A with a message identifier 502 (101101), stores the keyword(s) 504 ("I just bought via @amazon") used by the message retriever 402 when retrieving the asset-regarding social media message 114A, stores the asset identifier 120 (Twilight (book)) in the asset-regarding social media message 114A, and the message timestamp 116 retrieved by the timestamp retriever 406 (11/10/2013 at 9:45:05 a.m.) indicating when the asset-regarding social media message 114A was posted by the user.
corresponds to an asset of interest (e.g., includes a reference to the asset identifier 120). For example, in row 514, the user identifier 112 indicates that a user associated with the user identifier 112 (@user3) posted the corresponding asset-regarding social media message 114A.
Further, the AME server 108 identifies demographic information associated with the asset identifier 120 (necklace) and tags the user identifier 112 (@user3) with the corresponding demographics tag 126 (Tag C). In the illustrated example, the AME server 108 also stores additional information from the asset-regarding social media message 114A in the tagged identifier record. For example, in row 510, the tagged identifier logger 302 associates the asset-regarding social media message 114A with a message identifier 502 (101101), stores the keyword(s) 504 ("I just bought via @amazon") used by the message retriever 402 when retrieving the asset-regarding social media message 114A, stores the asset identifier 120 (Twilight (book)) in the asset-regarding social media message 114A, and the message timestamp 116 retrieved by the timestamp retriever 406 (11/10/2013 at 9:45:05 a.m.) indicating when the asset-regarding social media message 114A was posted by the user.
[0059] FIG. 6 illustrates an example data table 600 storing data representing estimated demographics of social media user identifiers that may be collected by the example AME server 108 of FIGS. 1, 3 and/or 4. In the illustrated example of FIG. 6, the data table 600 identifies a user identifier 112 and asset demographic information 124 tagged to the user identifier 112. In the illustrated example, the AME server 108 extracts the tagged identifier information from the tagged identifiers database 304. For example, the profile generator 306 may parse the tagged identifiers stored in the tagged identifiers database 304 and combine the records that correspond to the same user identifier 112. For example, in row 604, the asset demographic information 124 associated with the user identifier 112 (@user2) indicates that the user associated with the user identifier 112 (@user2) posted three asset-regarding social media messages 114A that were logged by the tagged identifier logger 302. Further, the data table 600 includes the results of the demographic analysis performed by the AME server 108 (e.g., demographics analysis results 610). For example, the demographics analyzer 310 may apply statistical methods such as Bayesian analysis to the different demographic segments associated with different asset-regarding social media messages 114A for which the same user is known to have sent the different messages 114A as determined by, for example, the user identifier 112 associated with the different asset-regarding social media messages 114A. In the illustrated example, the data table 600 includes estimated user demographic information 612 based on the corresponding demographics analysis results 610. In the illustrated example, the AME server 108 may identify the demographic segment with the highest likelihood as the demographics for the user (e.g., the estimated user demographic information 612). In some examples, when estimating the user demographic information 612, the percentages of the demographic analysis results 610 may be modified based on known social media usage patterns (e.g., if females less than age 20 are more likely to use social media than males less than age 20, the percentages of the demographic analysis results 610 may be weighted or otherwise adjusted to reflect those likelihoods).
[0060] Flowcharts representative of example machine readable instructions for implementing the AME server 108 of FIGS. 1, 3 and/or 4 are shown in FIGS. 7-9. In this example, the machine readable instructions comprise a program for execution by a processor such as the processor 1012 shown in the example processor platform 1000 discussed below in connection with FIG. 10. The program may be embodied in software stored on a tangible computer readable storage medium such as a CD-ROM, a floppy disk, a hard drive, a digital versatile disk (DVD), a Blu-ray disk, or a memory associated with the processor 1012, but the entire program and/or parts thereof could alternatively be executed by a device other than the processor 1012 and/or embodied in firmware or dedicated hardware. Further, although the example program is described with reference to the flowcharts illustrated in FIGS. 7-9, many other methods of implementing the example AME server 108 of FIGS. 1, 3 and/or 4 may alternatively be used.
For example, the order of execution of the blocks may be changed, and/or some of the blocks described may be changed, eliminated, or combined.
For example, the order of execution of the blocks may be changed, and/or some of the blocks described may be changed, eliminated, or combined.
[0061] As mentioned above, the example processes of FIGS. 7-9 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a tangible
62 PCT/US2014/052537 computer readable storage medium such as a hard disk drive, a flash memory, a read-only memory (ROM), a compact disk (CD), a digital versatile disk (DVD), a cache, a random-access memory (RAM) and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information). As used herein, the term tangible computer readable storage medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and to exclude transmission media. As used herein, "tangible computer readable storage medium" and "tangible machine readable storage medium" are used interchangeably. Additionally or alternatively, the example processes of FIGS. 7-9 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a non-transitory computer and/or machine readable medium such as a hard disk drive, a flash memory, a read-only memory, a compact disk, a digital versatile disk, a cache, a random-access memory and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information). As used herein, the term non-transitory computer readable medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and to exclude transmission media. As used herein, when the phrase "at least" is used as the transition term in a preamble of a claim, it is open-ended in the same manner as the term "comprising" is open ended.
[0062] The example program 700 of FIG. 7 estimates demographics of users employing social media at the example AME server 108 (FIGS. 1, 3 and/or 4). The example program 700 of FIG. 7 begins at block 702 when the AME server 108 identifies an asset-regarding social media message 114A. For example, the tagged identifier logger 302 (FIGS. 3 and/or 4) may retrieve the returned social media message 115 from the message hosting server 104 (FIG. 1) and analyze the text of the social media message 115 to determine whether a user posted the social media message 115 regarding an asset of interest (e.g., identified via a reference to an asset identifier 120) included in the reference database 118 (FIG. 1).
[0062] The example program 700 of FIG. 7 estimates demographics of users employing social media at the example AME server 108 (FIGS. 1, 3 and/or 4). The example program 700 of FIG. 7 begins at block 702 when the AME server 108 identifies an asset-regarding social media message 114A. For example, the tagged identifier logger 302 (FIGS. 3 and/or 4) may retrieve the returned social media message 115 from the message hosting server 104 (FIG. 1) and analyze the text of the social media message 115 to determine whether a user posted the social media message 115 regarding an asset of interest (e.g., identified via a reference to an asset identifier 120) included in the reference database 118 (FIG. 1).
[0063] At block 704, the AME server 108 determines asset demographic information associated with the asset of interest. For example, the tagged identifier logger 302 may retrieve asset demographic information 124 from the data table 200 stored in the reference database 118.
At block 706, the AME server 108 tags (e.g., associates) a user identifier associated with the asset-regarding social media message 114A with the determined asset demographic information 124. For example, the tagged identifier logger 302 may identify the user identifier 112 associated with the asset-regarding social media message 114A and tag the user identifier 112 with the asset demographic information 124. In some examples, the tagged identifier logger 302 records the tagged identifier in the tagged identifiers database 304 (FIG. 3).
At block 706, the AME server 108 tags (e.g., associates) a user identifier associated with the asset-regarding social media message 114A with the determined asset demographic information 124. For example, the tagged identifier logger 302 may identify the user identifier 112 associated with the asset-regarding social media message 114A and tag the user identifier 112 with the asset demographic information 124. In some examples, the tagged identifier logger 302 records the tagged identifier in the tagged identifiers database 304 (FIG. 3).
[0064] At block 708, the AME server 108 determines whether to generate a profile of a user associated with the user identifier 112. For example, the reporter 320 (FIG.
3) may query the profile generator 306 for a profile for a certain user. If, at block 708, the profile generator 306 determines to generate a user profile, then, at block 710, the profile generator 306 generates a user profile using demographic information tagged to the user identifier 112 associated with the user. For example, the profile generator 306 may identify one or more tagged identifiers that are associated with a user from the tagged identifiers database 304 and perform statistical analysis on the asset demographic information 124 tagged to the user identifier 112. In some examples, the profile generator 306 stores the generated user profile 128 in the profiles database 314 (FIG. 3).
3) may query the profile generator 306 for a profile for a certain user. If, at block 708, the profile generator 306 determines to generate a user profile, then, at block 710, the profile generator 306 generates a user profile using demographic information tagged to the user identifier 112 associated with the user. For example, the profile generator 306 may identify one or more tagged identifiers that are associated with a user from the tagged identifiers database 304 and perform statistical analysis on the asset demographic information 124 tagged to the user identifier 112. In some examples, the profile generator 306 stores the generated user profile 128 in the profiles database 314 (FIG. 3).
[0065] If, at block 708, the profile generator 306 determines not to generate the user profile 128 or after the profile generator 306 generates the user profile 128 at block 710, control proceeds to block 712 at which the AME server 108 determines whether to continue estimating demographics of users employing social media. If, at block 712, the AME server 108 determines to continue estimating demographics of users employing social media (e.g., the tagged identifier logger 302 is continuing to retrieve social media messages 115 from the message hosting server 104, the profile generator 306 is continuing to receive requests for user profiles 128, etc.), control returns to block 702 to identify another social media message associated with an asset (e.g., the asset-regarding social media message 114A). Otherwise, if, at block 712, the AME
server 108 determines to end estimating demographics of users employing social media (e.g., due to a server shutdown event, etc.), the example process 700 of FIG. 7 then ends.
server 108 determines to end estimating demographics of users employing social media (e.g., due to a server shutdown event, etc.), the example process 700 of FIG. 7 then ends.
[0066] The example program 800 of FIG. 8 tags a user identifier associated with asset-regarding social media messages with demographic information associated with the same asset of interest at the AME server 108 of FIGS. 1, 3 and/or 4. The example program of FIG. 8 may be used to implement blocks 702, 704 and 706 of FIG. 7. The example program 800 of FIG. 8 begins at block 802 at which the tagged identifier logger 302 (FIGS. 3 and/or 4) retrieves a social media message including one or more word(s) included in a keywords list. For example, the message retriever 402 may receive the social media message 115 in response to a query to the message hosting server 104 for social media messages 114 that include the one or more word(s) included in the keywords list 412.
[0067] At block 804, the tagged identifier logger 302 determines whether the returned social media message 115 references an asset of interest. For example, the message analyzer 404 may compare the text of the social media message 115 to asset identifiers 120 included in the data table 200. If, at block 804, the message analyzer 404 identifies a reference that matches (e.g., is the same or nearly the same as) an asset identifier 120, then, at block 806, the tagged identifier logger 302 retrieves the timestamp 116 associated with when the social media message 115 was posted (e.g., sent or conveyed by the message sender). For example, the timestamp retriever 406 may retrieve the message timestamp 116 from the text of the social media message 115. In some examples, the timestamp retriever 406 may request the message timestamp 116 from the media hosting server 104.
[0068] At block 808, the tagged identifier logger 302 determines whether characteristics of the social media message 115 satisfy one or more rule(s) (e.g., specific criteria) associated with the identified asset of interest. For example, the rules checker 408 may determine whether the message timestamp 116 is sufficiently near the broadcast time(s) of a television program to safely conclude exposure to the television program occurred by the user. In some examples, the rules checker 408 may determine whether the text of the social media message 115 includes a known vendor that supplies (e.g., distributes, sells and/or provides) the asset of interest. In some examples, the rules checker 408 may perform a time-series analysis of message timestamps 116 to determine a time-lag between real-time broadcast of a television program and when social media messages related to the television program are sent by users. The example rules checker 408 may use the time-lag to determine whether the social media message is sent by the user in response to the user viewing the television show (e.g., during or shortly after (e.g., within fifteen minutes of) broadcast of the television show).
[0069] If, at block 808, the rules checker 408 determines that the social media message 115 satisfies the one or more rule(s) associated with the identified asset of interest (e.g., the social media message 115 is an asset-regarding social media message 114A), then, at block 810, the tagged identifier logger 302 tags the user identifier associated with the asset-regarding social media message 114A with asset demographic information associated with the asset of interest.
For example, the identifier tagger 410 parses the asset-regarding social media message 114A to identify the user identifier 112. The identifier tagger 410 may also retrieve asset demographic information 124 from the data table 200 based on the asset identifier 120 identified in the asset-regarding social media message 114A and tag (e.g., associate) the asset demographic information 124 to the user identifier 112. At block 812, the tagged identifier logger 302 stores a record of the tagged identifier in the tagged identifiers database 304.
For example, the identifier tagger 410 parses the asset-regarding social media message 114A to identify the user identifier 112. The identifier tagger 410 may also retrieve asset demographic information 124 from the data table 200 based on the asset identifier 120 identified in the asset-regarding social media message 114A and tag (e.g., associate) the asset demographic information 124 to the user identifier 112. At block 812, the tagged identifier logger 302 stores a record of the tagged identifier in the tagged identifiers database 304.
[0070] If, at block 804, the message analyzer 404 determines that the social media message 115 does not include a reference to an asset of interest (e.g., the social media message 115 does not include a reference to an asset identifier 120 included the data table 200 and, thereby, is a non-asset regarding social media message 114B), or, if, at block 808, the rules checker 408 determines that the social media message 115 does not satisfy the one or more rule(s) associated with the asset of interest (e.g., the social media message 115 is a non-asset regarding social media message 114B), or after the tagged identifier logger 302 stores a record of the tagged identifier in the tagged identifiers database 304 at block 812, control proceeds to block 814 at which the tagged identifier logger 302 determines whether to continue to tag user identifiers with demographic information associated with identified assets of interest. If, at block 814, the tagged identifier logger 302 determines to continue tagging user identifiers with demographic information associated with identified assets of interest (e.g., the tagged identifier logger 302 is continuing to retrieve social media messages 115 from the message hosting server 104), control returns to block 804 to determine whether the returned social media message 115 references an asset of interest. Otherwise, if, at block 814, the tagged identifier logger 302 determines to end tagging user identifiers with demographic information associated with identified assets of interest (e.g., there are not additional social media messages to process, due to a server shutdown event, etc.), the example process 800 of FIG. 8 then ends.
[0071] The example program 900 of FIG. 9 generates a user profile estimating demographics of a user employing social media at the example AME server 108 (FIGS. 1, 3 and/or 4). The example program 900 of FIG. 9 may be used to implement block 710 of FIG. 7.
The example program 900 of FIG. 9 begins at block 902 when the AME server 108 identifies demographic information associated with a user identifier. For example, the demographics filterer 308 (FIG.
3) may parse the tagged identifier records stored in the tagged identifiers database 304 for the asset demographic information 124 tagged (e.g., associated) with the user identifier 112. In some examples, the demographics filterer 308 combines the asset demographic information 124 tagged with two or more user identifiers 112 that are associated with the same user.
The example program 900 of FIG. 9 begins at block 902 when the AME server 108 identifies demographic information associated with a user identifier. For example, the demographics filterer 308 (FIG.
3) may parse the tagged identifier records stored in the tagged identifiers database 304 for the asset demographic information 124 tagged (e.g., associated) with the user identifier 112. In some examples, the demographics filterer 308 combines the asset demographic information 124 tagged with two or more user identifiers 112 that are associated with the same user.
[0072] At block 904, the AME server 108 performs statistical analysis of the identified asset demographic information 124. For example, the demographics analyzer 310 (FIG.
3) may apply statistical methods such as Bayesian analysis to the asset demographic information 124 to determine the likelihood that the user fits into different demographic segments (e.g., the demographics analysis results 610 included in the data table 600). At block 906, the AME server 108 estimates the demographics for the user associated with the user identifier 112. For example, the estimator 312 (FIG. 3) may identify the demographic category (or categories) with the highest likelihood and associate the corresponding demographic category with the user (e.g., the estimated user demographic information 612 included in the data table 600). In general, larger numbers of tagged identifier records (and corresponding demographic information) associated with a given user over time increases the accuracy of the demographics imputations (e.g., the estimated user demographics).
3) may apply statistical methods such as Bayesian analysis to the asset demographic information 124 to determine the likelihood that the user fits into different demographic segments (e.g., the demographics analysis results 610 included in the data table 600). At block 906, the AME server 108 estimates the demographics for the user associated with the user identifier 112. For example, the estimator 312 (FIG. 3) may identify the demographic category (or categories) with the highest likelihood and associate the corresponding demographic category with the user (e.g., the estimated user demographic information 612 included in the data table 600). In general, larger numbers of tagged identifier records (and corresponding demographic information) associated with a given user over time increases the accuracy of the demographics imputations (e.g., the estimated user demographics).
[0073] At block 908, the AME server 108 stores a user profile for the user including the estimated user demographics for the user. For example, the profile generator 306 (FIG. 3) may generate the user profile 128 for the user using the estimated user demographic information 612 and store the generated user profile 128 in the profiles database 314 (FIG.
3). At block 910, the AME server 108 stores a timestamp with the estimated user demographic information 612. For example, the time stamper 316 (FIG. 3) may associate a time period (e.g., 1:00 a.m. Central Standard Time (CST) to 1:01 a.m. (CST) and/or a date (e.g., January 1, 2013) with each generated user profile 128 by, for example, appending the period of time and/or the date information to an end of the data in the user profile 128.
3). At block 910, the AME server 108 stores a timestamp with the estimated user demographic information 612. For example, the time stamper 316 (FIG. 3) may associate a time period (e.g., 1:00 a.m. Central Standard Time (CST) to 1:01 a.m. (CST) and/or a date (e.g., January 1, 2013) with each generated user profile 128 by, for example, appending the period of time and/or the date information to an end of the data in the user profile 128.
[0074] At block 912, the AME server 108 determines whether to continue generating user profiles. If, at block 912, the AME server 108 determines to continue generating user profiles (e.g., the profile generator 306 is continuing to receive requests for user profiles 128, etc.), control returns to block 902 to identify demographic information associated with another user.
Otherwise, if, at block 912, the AME server 108 determines to end generating user profiles (e.g., there are not additional requests to generate user profiles, due to a server shutdown event, etc.), the example process 900 of FIG. 9 then ends.
Otherwise, if, at block 912, the AME server 108 determines to end generating user profiles (e.g., there are not additional requests to generate user profiles, due to a server shutdown event, etc.), the example process 900 of FIG. 9 then ends.
[0075] FIG. 10 is a block diagram of an example processor platform 1000 capable of executing the instructions of FIGS. 7-9 to implement the example AME server 108 of FIGS. 1, 3 and/or 4. The processor platform 1000 can be, for example, a server, a personal computer, a mobile device (e.g., a cell phone, a smart phone, a tablet such as an iPad17\4), a personal digital assistant (PDA), an Internet appliance, a DVD player, a CD player, a digital video recorder, a Blu-ray player, a gaming console, a personal video recorder, a set top box, or any other type of computing device.
[0076] The processor platform 1000 of the illustrated example includes a processor 1012.
The processor 1012 of the illustrated example is hardware. For example, the processor 1012 can be implemented by one or more integrated circuits, logic circuits, microprocessors or controllers from any desired family or manufacturer.
The processor 1012 of the illustrated example is hardware. For example, the processor 1012 can be implemented by one or more integrated circuits, logic circuits, microprocessors or controllers from any desired family or manufacturer.
[0077] The processor 1012 of the illustrated example includes a local memory 1013 (e.g., a cache). The processor 1012 of the illustrated example is in communication with a main memory including a volatile memory 1014 and a non-volatile memory 1016 via a bus 1018. The volatile memory 1014 may be implemented by Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM) and/or any other type of random access memory device. The non-volatile memory 1016 may be implemented by flash memory and/or any other desired type of memory device. Access to the main memory 1014, 1016 is controlled by a memory controller.
[0078] The processor platform 1000 of the illustrated example also includes an interface circuit 1020. The interface circuit 1020 may be implemented by any type of interface standard, such as an Ethernet interface, a universal serial bus (USB), and/or a PCI
express interface.
express interface.
[0079] In the illustrated example, one or more input devices 1022 are connected to the interface circuit 1020. The input device(s) 1022 permit(s) a user to enter data and commands into the processor 1012. The input device(s) can be implemented by, for example, an audio sensor, a microphone, a camera (still or video), a keyboard, a button, a mouse, a touchscreen, a track-pad, a trackball, isopoint and/or a voice recognition system.
[0080] One or more output devices 1024 are also connected to the interface circuit 1020 of the illustrated example. The output devices 1024 can be implemented, for example, by display devices (e.g., a light emitting diode (LED), an organic light emitting diode (OLED), a liquid crystal display, a cathode ray tube display (CRT), a touchscreen, a tactile output device, a printer and/or speakers). The interface circuit 1020 of the illustrated example, thus, typically includes a graphics driver card, a graphics driver chip or a graphics driver processor.
[0081] The interface circuit 1020 of the illustrated example also includes a communication device such as a transmitter, a receiver, a transceiver, a modem and/or network interface card to facilitate exchange of data with external machines (e.g., computing devices of any kind) via a network 1026 (e.g., an Ethernet connection, a digital subscriber line (DSL), a telephone line, coaxial cable, a cellular telephone system, etc.).
[0082] The processor platform 1000 of the illustrated example also includes one or more mass storage devices 1028 for storing software and/or data. Examples of such mass storage devices 1028 include floppy disk drives, hard drive disks, compact disk drives, Blu-ray disk drives, RAID systems, and digital versatile disk (DVD) drives.
[0083] The coded instructions 1032 of FIGS. 7-9 may be stored in the mass storage device 1028, in the volatile memory 1014, in the non-volatile memory 1016, and/or on a removable tangible computer readable storage medium such as a CD or DVD.
[0084] From the foregoing, it will be appreciated that methods, apparatus and articles of manufacture have been disclosed which enable imputing demographic information of a known first group of people onto an unknown second group of people, and, thereby, enabling tracking the reach and effectiveness of an asset based on the reported exposure to the asset by the second group of people. Such imputations may be based on (1) posts made via social media sites by the second group of people and (2) demographics and media exposure data collected for the first group of people. The first group of people may be panelists of an audience and/or market research study.
[0085] Although certain example methods, apparatus and articles of manufacture have been disclosed herein, the scope of coverage of this patent is not limited thereto.
On the contrary, this patent covers all methods, apparatus and articles of manufacture fairly falling within the scope of the claims of this patent.
On the contrary, this patent covers all methods, apparatus and articles of manufacture fairly falling within the scope of the claims of this patent.
Claims (34)
1. A method to estimate demographics of a user of social media, the method comprising:
retrieving, by executing an instruction with a processor of an audience measurement entity, a plurality of electronically transmitted social media messages from a message hosting server based on media referenced in the plurality of electronically transmitted social media messages to reduce a set of social media messages for subsequent processing;
identifying, by executing an instruction with the processor, asset-regarding social media messages of the plurality of electronically transmitted social media messages based on references to assets in respective ones of the social media messages;
identifying, by executing an instruction with the processor, a first social media message of the asset-regarding social media messages mentioning a first asset, the first social media message of the asset-regarding social media messages originated by or received by the user via a computer networked social media service;
determining, by executing an instruction with the processor, first demographics associated with the first asset from a computer database based on a first asset identifier included in the computer database, the first asset identifier associated with the first asset, the first demographics including a first set of demographic categories, each demographic category including a likelihood of representing the first demographics;
in response to determining the first demographics associated with the first asset, associating, by executing an instruction with the processor, the first demographics with the user;
identifying, by executing an instruction with the processor, a second social media message of the asset-regarding social media messages mentioning a second asset, the second social media message of the asset-regarding social media messages originated by or received by the user via the computer networked social media service;
determining, by executing an instruction with the processor, second demographics associated with the second asset from the computer database based on a second asset identifier Date Recue/Date Received 2021-05-21 included in the computer database, the second asset identifier associated with the second asset, the second demographics including a second set of demographic categories, each demographic category including a likelihood of representing the second demographics;
tagging, by executing an instruction with the processor, a first user identifier with the first demographics and tagging a second user identifier with the second demographics;
based on the tagging, generating, by executing an instruction with the processor, a demographic profile for the user based on analyzing the likelihoods for each demographic category from the first demographics and the second demographics; and storing, by executing an instruction with the processor, the demographic profile in a memory of a profile database to reduce storage requirements.
retrieving, by executing an instruction with a processor of an audience measurement entity, a plurality of electronically transmitted social media messages from a message hosting server based on media referenced in the plurality of electronically transmitted social media messages to reduce a set of social media messages for subsequent processing;
identifying, by executing an instruction with the processor, asset-regarding social media messages of the plurality of electronically transmitted social media messages based on references to assets in respective ones of the social media messages;
identifying, by executing an instruction with the processor, a first social media message of the asset-regarding social media messages mentioning a first asset, the first social media message of the asset-regarding social media messages originated by or received by the user via a computer networked social media service;
determining, by executing an instruction with the processor, first demographics associated with the first asset from a computer database based on a first asset identifier included in the computer database, the first asset identifier associated with the first asset, the first demographics including a first set of demographic categories, each demographic category including a likelihood of representing the first demographics;
in response to determining the first demographics associated with the first asset, associating, by executing an instruction with the processor, the first demographics with the user;
identifying, by executing an instruction with the processor, a second social media message of the asset-regarding social media messages mentioning a second asset, the second social media message of the asset-regarding social media messages originated by or received by the user via the computer networked social media service;
determining, by executing an instruction with the processor, second demographics associated with the second asset from the computer database based on a second asset identifier Date Recue/Date Received 2021-05-21 included in the computer database, the second asset identifier associated with the second asset, the second demographics including a second set of demographic categories, each demographic category including a likelihood of representing the second demographics;
tagging, by executing an instruction with the processor, a first user identifier with the first demographics and tagging a second user identifier with the second demographics;
based on the tagging, generating, by executing an instruction with the processor, a demographic profile for the user based on analyzing the likelihoods for each demographic category from the first demographics and the second demographics; and storing, by executing an instruction with the processor, the demographic profile in a memory of a profile database to reduce storage requirements.
2. The method as defined in claim 1, wherein the identifying of the first social media message includes:
identifying a reference to the first asset in text of a social media message;
and determining whether a characteristic of the social media message satisfies a rule associated with the first asset.
identifying a reference to the first asset in text of a social media message;
and determining whether a characteristic of the social media message satisfies a rule associated with the first asset.
3. The method as defined in claim 2, wherein the first asset is a media event and the rule associated with the first asset specifies a relationship to a broadcast time of the asset.
4. The method as defined in claim 2, wherein the determining of whether the characteristic of the social media message satisfies the rule associated with the first asset further includes determining whether a timestamp associated with the social media message falls within a time period defined by the rule.
Date Recue/Date Received 2021-05-21
Date Recue/Date Received 2021-05-21
5. The method as defined in claim 2, wherein the first asset is a product and the rule associated with the first asset identifies a vendor that supplies the first asset.
6. The method as defined in claim 5, wherein the determining of whether the characteristic of the social media message satisfies the rule associated with the first asset further includes determining whether the text of the social media message mentions the vendor.
7. The method as defined in claim 6, wherein the first demographics are associated with a group of people who are purchasers of the first asset.
8. The method as defined in claim 1, wherein the first demographics are associated with a group of people who are an audience for the first asset.
9. The method as defined in claim 1, wherein the first social media message and the second social media message are associated with a first user identifier, the method further including:
identifying a third social media message mentioning a third asset, the third social media message associated with a second user identifier associated with the user, the second user identifier different than the first user identifier; and the estimating of the demographic profile for the user includes combining demographics associated with two or more different groups with which the first user identifier and the second user identifier are associated.
identifying a third social media message mentioning a third asset, the third social media message associated with a second user identifier associated with the user, the second user identifier different than the first user identifier; and the estimating of the demographic profile for the user includes combining demographics associated with two or more different groups with which the first user identifier and the second user identifier are associated.
10. The method as defined in claim 1, wherein the first demographics are associated with a first group of people who are included in an audience for the first asset and the second demographics are associated with a second group of people who are purchasers of the second asset.
Date Recue/Date Received 2021-05-21
Date Recue/Date Received 2021-05-21
11. The method as defined in claim 1, wherein the estimating of the demographic profile for the user further includes:
analyzing the first demographics and the second demographics;
determining a demographic category with a highest likelihood based on results of the analyzing; and associating the demographic category with the highest likelihood with the user.
analyzing the first demographics and the second demographics;
determining a demographic category with a highest likelihood based on results of the analyzing; and associating the demographic category with the highest likelihood with the user.
12. The method as defined in claim 11, wherein the analyzing of the first demographics and the second demographics includes performing Bayesian analysis on the first demographics and the second demographics.
13. The method as defined in claim 11, wherein the analyzing of the first demographics and the second demographics includes performing principal component analysis on the first demographics and the second demographics.
14. A system comprising:
a tagged identifier logger to:
retrieve a plurality of electronically transmitted social media messages from a message hosting server based on media referenced in the plurality of electronically transmitted social media messages to reduce a set of social media messages for subsequent processing;
identify, by executing an instruction with the processor, asset-regarding social media messages of a plurality of electronically transmitted social media messages based on references to assets in respective ones of the social media messages;
Date Recue/Date Received 2021-05-21 identify a first social media message of the asset-regarding social media messages mentioning a first asset, the first social media message of the asset-regarding social media messages originated by or received by a user via a computer networked social media service;
determine first demographics associated with the first asset from a computer database based on a first asset identifier included in the computer database, the first asset identifier associated with the first asset, the first demographics including a first set of demographic categories, each demographic category including a likelihood of representing the first demographics;
in response to determining the first demographics associated with the first asset, associate the first demographics with the user;
identify a second social media message of the asset-regarding social media messages mentioning a second asset, the second social media message of the asset-regarding social media messages originated by or received by the user via the computer networked social media service;
determine second demographics associated with the second asset from the computer database based on a second asset identifier included in the computer database, the second asset identifier associated with the second asset, the second demographics including a second set of demographic categories, each demographic category including a likelihood of representing the second demographics;
tag a first user identifier with the first demographics and tag a second user identifier with the second demographics; and a profile generator to, based on the tagging, generate a demographic profile for the user based on analyzing the likelihoods for each demographic category from the first demographics and the second demographics and store the demographic profile in a memory of a profile database to reduce storage requirements, Date Recue/Date Received 2021-05-21 at least one of the tagged identifier logger or the profile generator implemented by a logic circuit.
a tagged identifier logger to:
retrieve a plurality of electronically transmitted social media messages from a message hosting server based on media referenced in the plurality of electronically transmitted social media messages to reduce a set of social media messages for subsequent processing;
identify, by executing an instruction with the processor, asset-regarding social media messages of a plurality of electronically transmitted social media messages based on references to assets in respective ones of the social media messages;
Date Recue/Date Received 2021-05-21 identify a first social media message of the asset-regarding social media messages mentioning a first asset, the first social media message of the asset-regarding social media messages originated by or received by a user via a computer networked social media service;
determine first demographics associated with the first asset from a computer database based on a first asset identifier included in the computer database, the first asset identifier associated with the first asset, the first demographics including a first set of demographic categories, each demographic category including a likelihood of representing the first demographics;
in response to determining the first demographics associated with the first asset, associate the first demographics with the user;
identify a second social media message of the asset-regarding social media messages mentioning a second asset, the second social media message of the asset-regarding social media messages originated by or received by the user via the computer networked social media service;
determine second demographics associated with the second asset from the computer database based on a second asset identifier included in the computer database, the second asset identifier associated with the second asset, the second demographics including a second set of demographic categories, each demographic category including a likelihood of representing the second demographics;
tag a first user identifier with the first demographics and tag a second user identifier with the second demographics; and a profile generator to, based on the tagging, generate a demographic profile for the user based on analyzing the likelihoods for each demographic category from the first demographics and the second demographics and store the demographic profile in a memory of a profile database to reduce storage requirements, Date Recue/Date Received 2021-05-21 at least one of the tagged identifier logger or the profile generator implemented by a logic circuit.
15. The system as defined in claim 14, further including:
a message analyzer to determine whether the first social media message mentions the first asset; and a rules checker to determine whether a characteristic of the first social media message satisfies a rule associated with the first asset.
a message analyzer to determine whether the first social media message mentions the first asset; and a rules checker to determine whether a characteristic of the first social media message satisfies a rule associated with the first asset.
16. The system as defined in claim 15, wherein the first asset is a media event and the rule associated with the first asset specifies a relationship to a broadcast time of the first asset.
17. The system as defined in claim 16, wherein the rules checker is to determine whether the characteristic of the first social media message satisfies the rule associated with the first asset by determining whether a timestamp associated with the first social media message falls within a threshold time of the broadcast time of the first asset.
18. The system as defined in claim 16, wherein the first demographics are associated with a group of people who are included in an audience for the first asset.
19. The system as defined in claim 15, wherein the first asset is a product and the rule associated with the first asset specifies a vendor that supplies the first asset.
20. The system as defined in claim 19, wherein the rules checker is to determine whether the characteristic of the first social media message satisfies the rule associated with the first asset by determining whether the first social media message includes a reference to the vendor.
Date Recue/Date Received 2021-05-21
Date Recue/Date Received 2021-05-21
21. The system as defined in claim 19, wherein the first demographics are associated with a group of people who are purchasers of the first asset.
22. The system as defined in claim 14, wherein the first demographics are associated with a first group of people who are included in an audience for the first asset, and the second demographics are associated with a second group of people who are purchasers of the second asset.
23. The system as defined in claim 14, further including:
an analyzer to analyze the first demographics and the second demographics; and an estimator to determine a demographic category with a highest likelihood based on an output of the analyzer, the estimator to associate the demographic category with the highest likelihood with the user.
an analyzer to analyze the first demographics and the second demographics; and an estimator to determine a demographic category with a highest likelihood based on an output of the analyzer, the estimator to associate the demographic category with the highest likelihood with the user.
24. The system as defined in claim 23, wherein the analyzer applies Bayesian analysis to the first demographics and the second demographics.
25. The system as defined in claim 23, wherein the analyzer applies principal component analysis to the first demographics and the second demographics.
26. A tangible computer readable storage medium comprising instructions that, when executed, cause a processor to at least:
retrieve a plurality of electronically transmitted social media messages from a message hosting server based on media referenced in the plurality of electronically transmitted social media messages to reduce a set of social media messages for subsequent processing;
Date Recue/Date Received 2021-05-21 identify asset-regarding social media messages of a plurality of electronically transmitted social media messages based on references to assets in respective ones of the social media messages;
identify a first social media message of the asset-regarding social media messages mentioning a first asset, the first social media message of the asset-regarding social media messages originated by or received by a user via a computer networked social media service;
determine first demographics associated with the first asset from a computer database based on a first asset identifier included in the computer database, the first asset identifier associated with the first asset, the first demographics including a first set of demographic categories, each demographic category including a likelihood of representing the first demographics;
in response to determining the first demographics associated with the first asset, associate the first demographics with the user;
identify a second social media message of the asset-regarding social media messages mentioning a second asset, the second social media message of the asset-regarding social media messages originated by or received by the user via the computer networked social media service;
determine second demographics associated with the second asset from the computer database based on a second asset identifier included in the computer database, the second asset identifier associated with the second asset, the second demographics including a second set of demographic categories, each demographic category including a likelihood of representing the second demographics;
tag a first user identifier with the first demographics and tag a second user identifier with the second demographics;
based on the tagging, generate a demographic profile for the user based on analyzing the likelihoods for each demographic category from the first demographics and the second demographics; and Date Recue/Date Received 2021-05-21 store the demographic profile in a memory of a profile database to reduce storage requirements.
retrieve a plurality of electronically transmitted social media messages from a message hosting server based on media referenced in the plurality of electronically transmitted social media messages to reduce a set of social media messages for subsequent processing;
Date Recue/Date Received 2021-05-21 identify asset-regarding social media messages of a plurality of electronically transmitted social media messages based on references to assets in respective ones of the social media messages;
identify a first social media message of the asset-regarding social media messages mentioning a first asset, the first social media message of the asset-regarding social media messages originated by or received by a user via a computer networked social media service;
determine first demographics associated with the first asset from a computer database based on a first asset identifier included in the computer database, the first asset identifier associated with the first asset, the first demographics including a first set of demographic categories, each demographic category including a likelihood of representing the first demographics;
in response to determining the first demographics associated with the first asset, associate the first demographics with the user;
identify a second social media message of the asset-regarding social media messages mentioning a second asset, the second social media message of the asset-regarding social media messages originated by or received by the user via the computer networked social media service;
determine second demographics associated with the second asset from the computer database based on a second asset identifier included in the computer database, the second asset identifier associated with the second asset, the second demographics including a second set of demographic categories, each demographic category including a likelihood of representing the second demographics;
tag a first user identifier with the first demographics and tag a second user identifier with the second demographics;
based on the tagging, generate a demographic profile for the user based on analyzing the likelihoods for each demographic category from the first demographics and the second demographics; and Date Recue/Date Received 2021-05-21 store the demographic profile in a memory of a profile database to reduce storage requirements.
27. The tangible computer readable storage medium as defined in claim 26, wherein the instructions cause the processor to identify the first social media message by:
identifying a reference to the first asset in text of a social media message;
and determining whether a characteristic of the social media message satisfies a rule associated with the first asset.
identifying a reference to the first asset in text of a social media message;
and determining whether a characteristic of the social media message satisfies a rule associated with the first asset.
28. The tangible computer readable storage medium as defined in claim 27, wherein the first asset is a media event and the rule specifies a timeframe after a broadcast time of the first asset.
29. The tangible computer readable storage medium as defined in claim 28, wherein the instructions cause the processor to determine whether the characteristic of the first social media message satisfies the rule by determining whether a timestamp associated with the first social media message occurs within the timeframe.
30. The tangible computer readable storage medium as defined in claim 27, wherein the first asset is a product and wherein the rule specifies a vendor that supplies the first asset.
31. The tangible computer readable storage medium as defined in claim 30, wherein the instructions further cause the processor to determine whether the text of the first social media message mentions the vendor.
32. The tangible computer readable storage medium as defined in claim 26, wherein the instructions further cause the processor to:
Date Recue/Date Received 2021-05-21 analyze the first demographics and the second demographics;
determine a demographic category with a highest likelihood based on results of the analysis; and associate the demographic category with the highest likelihood with the user.
Date Recue/Date Received 2021-05-21 analyze the first demographics and the second demographics;
determine a demographic category with a highest likelihood based on results of the analysis; and associate the demographic category with the highest likelihood with the user.
33. The tangible computer readable storage medium as defined in claim 32, wherein the instructions cause the processor to analyze the first demographics and the second demographics by performing Bayesian analysis on the first demographics and the second demographics.
34. The tangible computer readable storage medium as defined in claim 32, wherein the instructions cause the processor to analyze the first demographics and the second demographics by performing principal component analysis on the first demographics and the second demographics.
Date Recue/Date Received 2021-05-21
Date Recue/Date Received 2021-05-21
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201361871243P | 2013-08-28 | 2013-08-28 | |
US61/871,243 | 2013-08-28 | ||
US14/142,411 US10333882B2 (en) | 2013-08-28 | 2013-12-27 | Methods and apparatus to estimate demographics of users employing social media |
US14/142,411 | 2013-12-27 | ||
PCT/US2014/052537 WO2015031262A1 (en) | 2013-08-28 | 2014-08-25 | Methods and apparatus to estimate demographics of users employing social media |
Publications (2)
Publication Number | Publication Date |
---|---|
CA2889349A1 CA2889349A1 (en) | 2015-03-05 |
CA2889349C true CA2889349C (en) | 2022-06-21 |
Family
ID=52584804
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CA2889349A Active CA2889349C (en) | 2013-08-28 | 2014-08-25 | Methods and apparatus to estimate demographics of users employing social media |
Country Status (10)
Country | Link |
---|---|
US (2) | US10333882B2 (en) |
EP (1) | EP3039875A4 (en) |
JP (1) | JP6115901B2 (en) |
KR (4) | KR102355826B1 (en) |
CN (1) | CN104756504A (en) |
AU (1) | AU2014311451A1 (en) |
BR (1) | BR112015009526A2 (en) |
CA (1) | CA2889349C (en) |
HK (1) | HK1212130A1 (en) |
WO (1) | WO2015031262A1 (en) |
Families Citing this family (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10333882B2 (en) | 2013-08-28 | 2019-06-25 | The Nielsen Company (Us), Llc | Methods and apparatus to estimate demographics of users employing social media |
US9344387B1 (en) * | 2014-02-08 | 2016-05-17 | Twitter, Inc. | Analysis of content sharing in a messaging platform |
US10535029B2 (en) | 2015-01-23 | 2020-01-14 | Sprinklr, Inc. | Multi-dimensional command center |
US10565601B2 (en) | 2015-02-27 | 2020-02-18 | The Nielsen Company (Us), Llc | Methods and apparatus to identify non-traditional asset-bundles for purchasing groups using social media |
US10219039B2 (en) | 2015-03-09 | 2019-02-26 | The Nielsen Company (Us), Llc | Methods and apparatus to assign viewers to media meter data |
US10045082B2 (en) | 2015-07-02 | 2018-08-07 | The Nielsen Company (Us), Llc | Methods and apparatus to correct errors in audience measurements for media accessed using over-the-top devices |
US20170090718A1 (en) * | 2015-09-25 | 2017-03-30 | International Business Machines Corporation | Linking selected messages in electronic message threads |
CN106557513B (en) * | 2015-09-29 | 2022-05-10 | 腾讯科技(深圳)有限公司 | Event information pushing method and event information pushing device |
US10187675B2 (en) | 2015-10-12 | 2019-01-22 | The Nielsen Company (Us), Llc | Methods and apparatus to identify co-relationships between media using social media |
CN108701322A (en) * | 2016-02-12 | 2018-10-23 | 开利公司 | The method for examining cold chain distribution system |
US9912424B2 (en) | 2016-05-27 | 2018-03-06 | The Nielsen Company (Us), Llc | Methods and apparatus to estimate ratings for media assets using social media |
US10546229B2 (en) * | 2016-06-02 | 2020-01-28 | Kodak Alaris Inc. | System and method for predictive curation, production infrastructure, and personal content assistant |
US10547906B2 (en) | 2016-06-07 | 2020-01-28 | The Nielsen Company (Us), Llc | Methods and apparatus to impute media consumption behavior |
US10600067B2 (en) * | 2016-06-16 | 2020-03-24 | Accenture Global Solutions Limited | Demographic based adjustment of data processing decision results |
US10791355B2 (en) | 2016-12-20 | 2020-09-29 | The Nielsen Company (Us), Llc | Methods and apparatus to determine probabilistic media viewing metrics |
CN107330091A (en) | 2017-07-04 | 2017-11-07 | 百度在线网络技术(北京)有限公司 | Information processing method and device |
US11810147B2 (en) * | 2017-10-19 | 2023-11-07 | Foursquare Labs, Inc. | Automated attribution modeling and measurement |
US11244363B1 (en) | 2018-10-25 | 2022-02-08 | Sprinklr, Inc. | Rating and review integration system |
US11386178B2 (en) | 2019-06-20 | 2022-07-12 | Sprinklr, Inc. | Enhanced notification system for real time control center |
US11397923B1 (en) | 2019-10-07 | 2022-07-26 | Sprinklr, Inc. | Dynamically adaptive organization mapping system |
US11966702B1 (en) * | 2020-08-17 | 2024-04-23 | Alphavu, Llc | System and method for sentiment and misinformation analysis of digital conversations |
US11645666B2 (en) * | 2021-01-28 | 2023-05-09 | Show Advertising Ltd. | Crowd demographic analysis |
Family Cites Families (207)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2176639B (en) | 1985-05-31 | 1988-11-23 | Mars Inc | Data acquisition system |
CA2041210C (en) | 1991-04-25 | 1998-12-29 | Michel Dufresne | Television audience data gathering |
JP3400068B2 (en) | 1994-03-18 | 2003-04-28 | 富士通株式会社 | Response amount prediction system |
CA2119970A1 (en) | 1994-03-25 | 1995-09-26 | Michael A. Lyons | Program monitoring system |
US5594934A (en) | 1994-09-21 | 1997-01-14 | A.C. Nielsen Company | Real time correlation meter |
US5758257A (en) | 1994-11-29 | 1998-05-26 | Herz; Frederick | System and method for scheduling broadcast of and access to video programs and other data using customer profiles |
WO1996028904A1 (en) | 1995-03-16 | 1996-09-19 | Bell Atlantic Network Services, Inc. | Simulcasting digital video programs for broadcast and interactive services |
US5675510A (en) | 1995-06-07 | 1997-10-07 | Pc Meter L.P. | Computer use meter and analyzer |
US5848396A (en) | 1996-04-26 | 1998-12-08 | Freedom Of Information, Inc. | Method and apparatus for determining behavioral profile of a computer user |
JP3191855B2 (en) | 1996-06-28 | 2001-07-23 | 日本電気株式会社 | MOVING IMAGE RECEIVING DEVICE AND METHOD FOR COMPENSING DISCARDED PACKET |
US6108637A (en) | 1996-09-03 | 2000-08-22 | Nielsen Media Research, Inc. | Content display monitor |
US5948061A (en) | 1996-10-29 | 1999-09-07 | Double Click, Inc. | Method of delivery, targeting, and measuring advertising over networks |
US6035339A (en) | 1997-03-13 | 2000-03-07 | At&T Corporation | Network information delivery system for delivering information based on end user terminal requirements |
US5796952A (en) | 1997-03-21 | 1998-08-18 | Dot Com Development, Inc. | Method and apparatus for tracking client interaction with a network resource and creating client profiles and resource database |
US6643696B2 (en) | 1997-03-21 | 2003-11-04 | Owen Davis | Method and apparatus for tracking client interaction with a network resource and creating client profiles and resource database |
US6098093A (en) | 1998-03-19 | 2000-08-01 | International Business Machines Corp. | Maintaining sessions in a clustered server environment |
US7240022B1 (en) | 1998-05-19 | 2007-07-03 | Mypoints.Com Inc. | Demographic information gathering and incentive award system and method |
US6434614B1 (en) | 1998-05-29 | 2002-08-13 | Nielsen Media Research, Inc. | Tracking of internet advertisements using banner tags |
US6223215B1 (en) | 1998-09-22 | 2001-04-24 | Sony Corporation | Tracking a user's purchases on the internet by associating the user with an inbound source and a session identifier |
US20020111172A1 (en) * | 2001-02-14 | 2002-08-15 | Dewolf Frederik M. | Location based profiling |
US7949565B1 (en) | 1998-12-03 | 2011-05-24 | Prime Research Alliance E., Inc. | Privacy-protected advertising system |
US20010049620A1 (en) | 2000-02-29 | 2001-12-06 | Blasko John P. | Privacy-protected targeting system |
US6055573A (en) | 1998-12-30 | 2000-04-25 | Supermarkets Online, Inc. | Communicating with a computer based on an updated purchase behavior classification of a particular consumer |
US6460079B1 (en) | 1999-03-04 | 2002-10-01 | Nielsen Media Research, Inc. | Method and system for the discovery of cookies and other client information |
US6529952B1 (en) | 1999-04-02 | 2003-03-04 | Nielsen Media Research, Inc. | Method and system for the collection of cookies and other information from a panel |
US7523191B1 (en) | 2000-06-02 | 2009-04-21 | Yahoo! Inc. | System and method for monitoring user interaction with web pages |
US6102406A (en) | 1999-06-07 | 2000-08-15 | Steven A. Miles | Internet-based advertising scheme employing scavenger hunt metaphor |
US7010497B1 (en) | 1999-07-08 | 2006-03-07 | Dynamiclogic, Inc. | System and method for evaluating and/or monitoring effectiveness of on-line advertising |
AUPQ206399A0 (en) | 1999-08-06 | 1999-08-26 | Imr Worldwide Pty Ltd. | Network user measurement system and method |
US6415323B1 (en) | 1999-09-03 | 2002-07-02 | Fastforward Networks | Proximity-based redirection system for robust and scalable service-node location in an internetwork |
US8108245B1 (en) | 1999-09-17 | 2012-01-31 | Cox Communications, Inc. | Method and system for web user profiling and selective content delivery |
US6839680B1 (en) | 1999-09-30 | 2005-01-04 | Fujitsu Limited | Internet profiling |
US6691163B1 (en) | 1999-12-23 | 2004-02-10 | Alexa Internet | Use of web usage trail data to identify related links |
US6993590B1 (en) | 2000-01-13 | 2006-01-31 | Inktomi Corporation | Method of creating data streams for user-specific usage data gathering systems |
US7065503B2 (en) | 2000-01-14 | 2006-06-20 | Matsushita Electric Industrial Co., Ltd. | Cookie data stored on transportable recording medium |
US7181412B1 (en) | 2000-03-22 | 2007-02-20 | Comscore Networks Inc. | Systems and methods for collecting consumer data |
US7260837B2 (en) | 2000-03-22 | 2007-08-21 | Comscore Networks, Inc. | Systems and methods for user identification, user demographic reporting and collecting usage data usage biometrics |
JP2001338176A (en) | 2000-03-23 | 2001-12-07 | Casio Comput Co Ltd | Method and system for information transmission and intermediation |
JP2001282982A (en) | 2000-03-28 | 2001-10-12 | Hisahiro Negi | Web marketing system |
US7039699B1 (en) | 2000-05-02 | 2006-05-02 | Microsoft Corporation | Tracking usage behavior in computer systems |
US7962603B1 (en) | 2000-06-06 | 2011-06-14 | Nobuyoshi Morimoto | System and method for identifying individual users accessing a web site |
JP2001357192A (en) | 2000-06-12 | 2001-12-26 | Toshiba Corp | Method and system for customer awareness research and storage medium storing program |
EP1222599A2 (en) | 2000-07-18 | 2002-07-17 | Yahoo Inc. | System and method for selecting alternative advertising inventory in place of sold out advertising inventory |
KR20020037980A (en) | 2000-11-16 | 2002-05-23 | 김형순 | System for retrieving and providing information |
JP2002163562A (en) | 2000-11-27 | 2002-06-07 | Dainippon Printing Co Ltd | Information distribution server device |
US6879960B2 (en) | 2000-12-01 | 2005-04-12 | Claritas, Inc. | Method and system for using customer preferences in real time to customize a commercial transaction |
US20030006911A1 (en) | 2000-12-22 | 2003-01-09 | The Cadre Group Inc. | Interactive advertising system and method |
US7266687B2 (en) | 2001-02-16 | 2007-09-04 | Motorola, Inc. | Method and apparatus for storing and distributing encryption keys |
JP4248183B2 (en) | 2001-02-26 | 2009-04-02 | パナソニック株式会社 | Cookie processing program and image data display device |
AU2002305137A1 (en) | 2001-04-06 | 2002-10-21 | Predictive Media Corporation | Method and apparatus for identifying unique client users from user behavioral data |
WO2002084507A1 (en) | 2001-04-13 | 2002-10-24 | Netiq Corporation | User-side tracking of multimedia application usage within a web page |
US20030037131A1 (en) | 2001-08-17 | 2003-02-20 | International Business Machines Corporation | User information coordination across multiple domains |
JPWO2003027860A1 (en) | 2001-09-19 | 2005-01-13 | 株式会社エヌ・ティ・ティ・アド | Content distribution system for distributing content changing on time axis, content distribution server, log collection server, content relay server, user terminal, content viewing state grasping method, recommendation method, and content providing method |
US6877007B1 (en) | 2001-10-16 | 2005-04-05 | Anna M. Hentzel | Method and apparatus for tracking a user's interaction with a resource supplied by a server computer |
US7343417B2 (en) | 2001-11-30 | 2008-03-11 | Knowledge Networks, Inc. | System and method for rating media information |
US20030177488A1 (en) | 2002-03-12 | 2003-09-18 | Smith Geoff S. | Systems and methods for media audience measurement |
US9235849B2 (en) | 2003-12-31 | 2016-01-12 | Google Inc. | Generating user information for use in targeted advertising |
US20030229884A1 (en) | 2002-05-21 | 2003-12-11 | Hewlett-Packard Development Company | Interaction manager template |
US20040088212A1 (en) | 2002-10-31 | 2004-05-06 | Hill Clarke R. | Dynamic audience analysis for computer content |
CA2520117A1 (en) | 2003-03-25 | 2004-10-14 | Sedna Patent Services, Llc | Generating audience analytics |
CA2686265A1 (en) | 2003-06-17 | 2004-12-17 | Ibm Canada Limited - Ibm Canada Limitee | Multiple identity management in an electronic commerce site |
US8464290B2 (en) | 2003-08-01 | 2013-06-11 | Tacoda, Inc. | Network for matching an audience with deliverable content |
WO2005024689A1 (en) | 2003-09-04 | 2005-03-17 | Interscope Inc. | Nsumer’s purchase behavior analysis method and device |
US20050144069A1 (en) | 2003-12-23 | 2005-06-30 | Wiseman Leora R. | Method and system for providing targeted graphical advertisements |
US7792954B2 (en) | 2004-04-02 | 2010-09-07 | Webtrends, Inc. | Systems and methods for tracking web activity |
US20050267799A1 (en) | 2004-05-10 | 2005-12-01 | Wesley Chan | System and method for enabling publishers to select preferred types of electronic documents |
US7546370B1 (en) | 2004-08-18 | 2009-06-09 | Google Inc. | Search engine with multiple crawlers sharing cookies |
JP2006127321A (en) | 2004-10-29 | 2006-05-18 | Solid Technology Kk | Terminal attribute addition device and terminal attribute addition method |
JP2006127320A (en) | 2004-10-29 | 2006-05-18 | Solid Technology Kk | Terminal attribute estimation apparatus and terminal attribute estimation method |
US20060168613A1 (en) | 2004-11-29 | 2006-07-27 | Wood Leslie A | Systems and processes for use in media and/or market research |
US8131861B2 (en) | 2005-05-20 | 2012-03-06 | Webtrends, Inc. | Method for cross-domain tracking of web site traffic |
US8312172B2 (en) | 2005-05-26 | 2012-11-13 | Bytemobile, Inc. | Method and system for delta compression |
US20080109306A1 (en) * | 2005-06-15 | 2008-05-08 | Maigret Robert J | Media marketplaces |
JP4764103B2 (en) | 2005-08-18 | 2011-08-31 | 株式会社東芝 | Content data distribution system and information processing apparatus |
CN100452781C (en) | 2005-10-26 | 2009-01-14 | 华为技术有限公司 | Method for transmitting partial unavailable information to destination user |
US20080086356A1 (en) | 2005-12-09 | 2008-04-10 | Steve Glassman | Determining advertisements using user interest information and map-based location information |
US20090030780A1 (en) | 2006-01-03 | 2009-01-29 | Ds-Iq, Inc. | Measuring effectiveness of marketing campaigns presented on media devices in public places using audience exposure data |
JP2007201742A (en) * | 2006-01-25 | 2007-08-09 | Ntt Software Corp | Content distribution system |
JP5034279B2 (en) * | 2006-03-15 | 2012-09-26 | 富士通株式会社 | Attribute estimation program and attribute information providing system |
EP2011002B1 (en) | 2006-03-27 | 2016-06-22 | Nielsen Media Research, Inc. | Methods and systems to meter media content presented on a wireless communication device |
US7941525B1 (en) | 2006-04-01 | 2011-05-10 | ClickTale, Ltd. | Method and system for monitoring an activity of a user |
US20080004958A1 (en) | 2006-06-29 | 2008-01-03 | Tony Ralph | Client side counting verification testing |
CN100456298C (en) | 2006-07-12 | 2009-01-28 | 百度在线网络技术(北京)有限公司 | Advertisement information retrieval system and method therefor |
US7933843B1 (en) * | 2006-08-26 | 2011-04-26 | CommEq Ltd. | Media-based computational influencer network analysis |
US7996456B2 (en) | 2006-09-20 | 2011-08-09 | John Nicholas and Kristin Gross Trust | Document distribution recommender system and method |
US20080147487A1 (en) | 2006-10-06 | 2008-06-19 | Technorati Inc. | Methods and apparatus for conversational advertising |
US20090132349A1 (en) | 2006-10-09 | 2009-05-21 | Splashcast Corp. | Targeted-demographic rich-media content, branding, and syndicated user-node distribution |
US20080104225A1 (en) | 2006-11-01 | 2008-05-01 | Microsoft Corporation | Visualization application for mining of social networks |
US8196166B2 (en) * | 2006-12-21 | 2012-06-05 | Verizon Patent And Licensing Inc. | Content hosting and advertising systems and methods |
US8700457B2 (en) | 2007-01-03 | 2014-04-15 | William H. Bollman | Mobile phone based rebate device for redemption at a point of sale terminal |
CN101222348B (en) | 2007-01-10 | 2011-05-11 | 阿里巴巴集团控股有限公司 | Method and system for calculating number of website real user |
US20080215607A1 (en) * | 2007-03-02 | 2008-09-04 | Umbria, Inc. | Tribe or group-based analysis of social media including generating intelligence from a tribe's weblogs or blogs |
US7996519B1 (en) | 2007-03-07 | 2011-08-09 | Comscore, Inc. | Detecting content and user response to content |
KR100910517B1 (en) | 2007-03-21 | 2009-07-31 | 엔에이치엔비즈니스플랫폼 주식회사 | System and method for expanding target inventory according to borwser-login mapping |
US20080250450A1 (en) | 2007-04-06 | 2008-10-09 | Adisn, Inc. | Systems and methods for targeted advertising |
US8229458B2 (en) | 2007-04-08 | 2012-07-24 | Enhanced Geographic Llc | Systems and methods to determine the name of a location visited by a user of a wireless device |
US20080276179A1 (en) | 2007-05-05 | 2008-11-06 | Intapp Inc. | Monitoring and Aggregating User Activities in Heterogeneous Systems |
US20090217315A1 (en) | 2008-02-26 | 2009-08-27 | Cognovision Solutions Inc. | Method and system for audience measurement and targeting media |
WO2009002949A2 (en) * | 2007-06-23 | 2008-12-31 | Motivepath, Inc. | System, method and apparatus for predictive modeling of specially distributed data for location based commercial services |
US7890592B2 (en) | 2007-06-29 | 2011-02-15 | Microsoft Corporation | Processing data obtained from a presence-based system |
US8229780B2 (en) | 2007-07-30 | 2012-07-24 | Silvercarrot, Inc. | System and method for online lead generation |
US7698422B2 (en) | 2007-09-10 | 2010-04-13 | Specific Media, Inc. | System and method of determining user demographic profiles of anonymous users |
US20090076899A1 (en) | 2007-09-14 | 2009-03-19 | Gbodimowo Gbeminiyi A | Method for analyzing, searching for, and trading targeted advertisement spaces |
US8302120B2 (en) | 2008-02-19 | 2012-10-30 | The Nielsen Company (Us), Llc | Methods and apparatus to monitor advertisement exposure |
US8112301B2 (en) | 2008-04-14 | 2012-02-07 | Tra, Inc. | Using consumer purchase behavior for television targeting |
WO2009146197A1 (en) | 2008-04-17 | 2009-12-03 | Arbitron Inc. | Cross-media interactivity metrics |
US8380562B2 (en) | 2008-04-25 | 2013-02-19 | Cisco Technology, Inc. | Advertisement campaign system using socially collaborative filtering |
US9384186B2 (en) | 2008-05-20 | 2016-07-05 | Aol Inc. | Monitoring conversations to identify topics of interest |
US9083853B2 (en) | 2008-06-02 | 2015-07-14 | Intent IQ, LLC | Targeted television advertisements associated with online users' preferred television programs or channels |
US20100030648A1 (en) * | 2008-08-01 | 2010-02-04 | Microsoft Corporation | Social media driven advertisement targeting |
US8549163B2 (en) | 2008-09-18 | 2013-10-01 | Jonathan M. Urdan | Passive parameter based demographics generation |
US20100088152A1 (en) | 2008-10-02 | 2010-04-08 | Dominic Bennett | Predicting user response to advertisements |
AU2008363490A1 (en) | 2008-10-28 | 2010-05-06 | Norwell Sa | Audience measurement system |
KR101066619B1 (en) * | 2008-11-07 | 2011-09-22 | 주식회사 케이티 | Prediction system and method using USSD message |
US20100121676A1 (en) | 2008-11-11 | 2010-05-13 | Yahoo! Inc. | Method and system for logging impressions of online advertisments |
JP2010134733A (en) * | 2008-12-05 | 2010-06-17 | Dainippon Printing Co Ltd | Information recommendation device, information recommendation method, and program |
US20100153175A1 (en) | 2008-12-12 | 2010-06-17 | At&T Intellectual Property I, L.P. | Correlation of Psycho-Demographic Data and Social Network Data to Initiate an Action |
US8356247B2 (en) | 2008-12-16 | 2013-01-15 | Rich Media Worldwide, Llc | Content rendering control system and method |
US8462160B2 (en) | 2008-12-31 | 2013-06-11 | Facebook, Inc. | Displaying demographic information of members discussing topics in a forum |
US20100179856A1 (en) | 2009-01-14 | 2010-07-15 | Yahoo! Inc. | Conditional incentive presentation, tracking and redemption |
EP2382723A4 (en) | 2009-01-29 | 2013-10-09 | Nielsen Co Us Llc | Methods and apparatus to measure market statistics |
US20100205057A1 (en) | 2009-02-06 | 2010-08-12 | Rodney Hook | Privacy-sensitive methods, systems, and media for targeting online advertisements using brand affinity modeling |
KR101168705B1 (en) | 2009-02-18 | 2012-08-02 | 김기미 | Customized and intellectual symbol, icon internet information searching system utilizing a mobile communication terminal and IP-based information terminal |
GB2524907A (en) | 2009-03-06 | 2015-10-07 | Appnexus Inc | A computer system |
CN101505247A (en) | 2009-03-09 | 2009-08-12 | 成都市华为赛门铁克科技有限公司 | Detection method and apparatus for number of shared access hosts |
US8150974B2 (en) | 2009-03-17 | 2012-04-03 | Kindsight, Inc. | Character differentiation system generating session fingerprint using events associated with subscriber ID and session ID |
US8266687B2 (en) | 2009-03-27 | 2012-09-11 | Sophos Plc | Discovery of the use of anonymizing proxies by analysis of HTTP cookies |
JP5492630B2 (en) | 2009-03-31 | 2014-05-14 | 株式会社ビデオリサーチ | Content contact investigation system and content contact investigation method |
US10008212B2 (en) | 2009-04-17 | 2018-06-26 | The Nielsen Company (Us), Llc | System and method for utilizing audio encoding for measuring media exposure with environmental masking |
US20100268540A1 (en) | 2009-04-17 | 2010-10-21 | Taymoor Arshi | System and method for utilizing audio beaconing in audience measurement |
US20100268573A1 (en) | 2009-04-17 | 2010-10-21 | Anand Jain | System and method for utilizing supplemental audio beaconing in audience measurement |
JP2012526314A (en) | 2009-05-08 | 2012-10-25 | ゾケム オーワイ | System and method for analyzing behavioral and contextual data |
US20100325051A1 (en) | 2009-06-22 | 2010-12-23 | Craig Stephen Etchegoyen | System and Method for Piracy Reduction in Software Activation |
US9178634B2 (en) | 2009-07-15 | 2015-11-03 | Time Warner Cable Enterprises Llc | Methods and apparatus for evaluating an audience in a content-based network |
US8412796B2 (en) | 2009-07-31 | 2013-04-02 | University College Dublin—National University of Ireland, Dublin | Real time information feed processing |
US8612860B2 (en) | 2009-08-12 | 2013-12-17 | Warner Music Inc. | Systems, methods, and media for coordinating the presentation of media with an event |
US9529864B2 (en) | 2009-08-28 | 2016-12-27 | Microsoft Technology Licensing, Llc | Data mining electronic communications |
US20120192214A1 (en) | 2009-12-22 | 2012-07-26 | Resonate Networks | Method and apparatus for delivering targeted content to television viewers |
KR101118741B1 (en) | 2009-08-31 | 2012-03-12 | 주식회사 나스미디어 | A method for providing internet advertisement popularity rating |
US20110087519A1 (en) | 2009-10-09 | 2011-04-14 | Visa U.S.A. Inc. | Systems and Methods for Panel Enhancement with Transaction Data |
US8595058B2 (en) | 2009-10-15 | 2013-11-26 | Visa U.S.A. | Systems and methods to match identifiers |
WO2011072062A2 (en) | 2009-12-08 | 2011-06-16 | Adxpose, Inc. | Systems and methods for capturing and reporting metrics regarding user engagement including a canvas model |
US20110191184A1 (en) | 2010-01-29 | 2011-08-04 | Bank Of America Corporation | Mobile location integrated merchant offer program and customer shopping |
US20110246306A1 (en) | 2010-01-29 | 2011-10-06 | Bank Of America Corporation | Mobile location tracking integrated merchant offer program and customer shopping |
US20110191664A1 (en) | 2010-02-04 | 2011-08-04 | At&T Intellectual Property I, L.P. | Systems for and methods for detecting url web tracking and consumer opt-out cookies |
WO2011097624A2 (en) | 2010-02-08 | 2011-08-11 | Facebook, Inc. | Communicating information in a social network system about activities from another domain |
US8595789B2 (en) | 2010-02-15 | 2013-11-26 | Bank Of America Corporation | Anomalous activity detection |
US20120310729A1 (en) | 2010-03-16 | 2012-12-06 | Dalto John H | Targeted learning in online advertising auction exchanges |
US9946775B2 (en) | 2010-03-24 | 2018-04-17 | Taykey Ltd. | System and methods thereof for detection of user demographic information |
KR101682579B1 (en) | 2010-03-30 | 2016-12-05 | 삼성전자 주식회사 | Method and apparatus for providing character inputting virtual keypad in a touch terminal |
US8626901B2 (en) | 2010-04-05 | 2014-01-07 | Comscore, Inc. | Measurements based on panel and census data |
US8775400B2 (en) * | 2010-06-30 | 2014-07-08 | Microsoft Corporation | Extracting facts from social network messages |
US8307006B2 (en) | 2010-06-30 | 2012-11-06 | The Nielsen Company (Us), Llc | Methods and apparatus to obtain anonymous audience measurement data from network server data for particular demographic and usage profiles |
CA2806881C (en) * | 2010-07-26 | 2016-06-14 | Invidi Technologies Corporation | Universally interactive request for information |
US9747605B2 (en) | 2010-08-02 | 2017-08-29 | Facebook, Inc. | Measuring quality of user interaction with third party content |
MX2013001160A (en) | 2010-08-10 | 2013-03-22 | Ericsson Telefon Ab L M | Aggregating demographic distribution information. |
US8886773B2 (en) | 2010-08-14 | 2014-11-11 | The Nielsen Company (Us), Llc | Systems, methods, and apparatus to monitor mobile internet activity |
US9262517B2 (en) | 2010-08-18 | 2016-02-16 | At&T Intellectual Property I, L.P. | Systems and methods for social media data mining |
CA3027898C (en) | 2010-09-22 | 2023-01-17 | The Nielsen Company (Us), Llc | Methods and apparatus to determine impressions using distributed demographic information |
US9092797B2 (en) | 2010-09-22 | 2015-07-28 | The Nielsen Company (Us), Llc | Methods and apparatus to analyze and adjust demographic information |
AU2013203898B2 (en) | 2010-09-22 | 2015-07-02 | The Nielsen Company (Us), Llc | Methods and apparatus to determine impressions using distributed demographic information |
US8484241B2 (en) | 2010-10-29 | 2013-07-09 | Russell Kent Bouse | Systems and methods to consolidate and communicate user profiles and modality preferences information for content delivery or interaction experiences |
US8495143B2 (en) | 2010-10-29 | 2013-07-23 | Facebook, Inc. | Inferring user profile attributes from social information |
US10248960B2 (en) * | 2010-11-16 | 2019-04-02 | Disney Enterprises, Inc. | Data mining to determine online user responses to broadcast messages |
US20120130802A1 (en) | 2010-11-19 | 2012-05-24 | Jerome Shimizu | Systems, methods and apparatus to design an advertising campaign |
US8631122B2 (en) * | 2010-11-29 | 2014-01-14 | Viralheat, Inc. | Determining demographics based on user interaction |
WO2012078662A1 (en) | 2010-12-06 | 2012-06-14 | Campaigngrid, Llc | Electronic and network-based franking |
US9009298B2 (en) | 2010-12-10 | 2015-04-14 | The Nielsen Company (Us), Llc | Methods and apparatus to determine audience engagement indices associated with media presentations |
US8468559B2 (en) | 2010-12-13 | 2013-06-18 | Google Inc. | Inferring demographic compositions of television audiences |
US9497154B2 (en) | 2010-12-13 | 2016-11-15 | Facebook, Inc. | Measuring social network-based interaction with web content external to a social networking system |
US20120323675A1 (en) | 2010-12-15 | 2012-12-20 | Ari Paparo | Methods and apparatus to measure comparative performance of internet and television ad campaigns |
EP2656297B1 (en) | 2010-12-20 | 2024-07-17 | The Nielsen Company (US), LLC | Methods and apparatus to determine media impressions using distributed demographic information |
US8874639B2 (en) | 2010-12-22 | 2014-10-28 | Facebook, Inc. | Determining advertising effectiveness outside of a social networking system |
US20120173701A1 (en) | 2010-12-30 | 2012-07-05 | Arbitron Inc. | Matching techniques for cross-platform monitoring and information |
US20120209920A1 (en) | 2011-02-10 | 2012-08-16 | Microsoft Corporation | Social influencers discovery |
US8700543B2 (en) * | 2011-02-12 | 2014-04-15 | Red Contexto Ltd. | Web page analysis system for computerized derivation of webpage audience characteristics |
US20120209918A1 (en) * | 2011-02-15 | 2012-08-16 | Shesha Shah | Social Net Advocacy Measure |
WO2012128895A2 (en) | 2011-03-18 | 2012-09-27 | The Nielsen Company (Us), Llc | Methods and apparatus to determine media impressions |
US8315620B1 (en) | 2011-05-27 | 2012-11-20 | The Nielsen Company (Us), Llc | Methods and apparatus to associate a mobile device with a panelist profile |
US9282158B2 (en) | 2011-06-06 | 2016-03-08 | Google Inc. | Reducing redirects |
US8560683B2 (en) | 2011-06-10 | 2013-10-15 | Google Inc. | Video and site analytics |
US9515904B2 (en) | 2011-06-21 | 2016-12-06 | The Nielsen Company (Us), Llc | Monitoring streaming media content |
US20120331561A1 (en) * | 2011-06-22 | 2012-12-27 | Broadstone Andrew J | Method of and Systems for Privacy Preserving Mobile Demographic Measurement of Individuals, Groups and Locations Over Time and Space |
US20130060629A1 (en) | 2011-09-07 | 2013-03-07 | Joshua Rangsikitpho | Optimization of Content Placement |
US10217117B2 (en) * | 2011-09-15 | 2019-02-26 | Stephan HEATH | System and method for social networking interactions using online consumer browsing behavior, buying patterns, advertisements and affiliate advertising, for promotions, online coupons, mobile services, products, goods and services, entertainment and auctions, with geospatial mapping technology |
US20130080263A1 (en) | 2011-09-23 | 2013-03-28 | Jonathan Goldman | Per-view charging for video advertisements |
US20130124478A1 (en) | 2011-11-11 | 2013-05-16 | Simply Measured, Inc. | Data analytics reporting system and methods |
US8509816B2 (en) * | 2011-11-11 | 2013-08-13 | International Business Machines Corporation | Data pre-fetching based on user demographics |
US20130151311A1 (en) | 2011-11-15 | 2013-06-13 | Bradley Hopkins Smallwood | Prediction of consumer behavior data sets using panel data |
WO2013078640A1 (en) * | 2011-11-30 | 2013-06-06 | Google Inc. | Estimating user demographics |
US9331975B2 (en) | 2011-12-16 | 2016-05-03 | The Nielsen Company (Us), Llc | Systems, methods, and apparatus to identify media presentation devices |
CA2863531A1 (en) | 2012-02-02 | 2013-08-08 | Unityworks! Media, Inc. | Method and system for creating data-driven multimedia advertisements for dynamically targeted audience |
US9015255B2 (en) | 2012-02-14 | 2015-04-21 | The Nielsen Company (Us), Llc | Methods and apparatus to identify session users with cookie information |
US9659105B2 (en) | 2012-03-15 | 2017-05-23 | The Nielsen Company (Us), Llc | Methods and apparatus to track web browsing sessions |
US20130282817A1 (en) * | 2012-03-22 | 2013-10-24 | Gerard J. Montgomery | Targeting Media Based on Viewer Attributes and Elements |
US9516360B2 (en) | 2012-04-12 | 2016-12-06 | Qualcomm Incorporated | Estimating demographic statistics of media viewership via context aware mobile devices |
AU2013204865B2 (en) | 2012-06-11 | 2015-07-09 | The Nielsen Company (Us), Llc | Methods and apparatus to share online media impressions data |
US20130346154A1 (en) * | 2012-06-22 | 2013-12-26 | Josephine Holz | Systems and methods for audience measurement analysis |
CN108648010B (en) * | 2012-09-18 | 2021-11-05 | 北京一点网聚科技有限公司 | Method, system and corresponding medium for providing content to a user |
US20140149422A1 (en) * | 2012-11-28 | 2014-05-29 | Dell Products L.P. | Automating Management of Social Media Data |
US9055021B2 (en) | 2012-11-30 | 2015-06-09 | The Nielsen Company (Us), Llc | Methods and apparatus to monitor impressions of social media messages |
US8935713B1 (en) | 2012-12-17 | 2015-01-13 | Tubular Labs, Inc. | Determining audience members associated with a set of videos |
US9609386B2 (en) | 2012-12-18 | 2017-03-28 | Rentak Corporation | System and methods for analyzing content engagement in conjunction with social media |
US9832155B2 (en) | 2013-01-31 | 2017-11-28 | The Nielsen Company (Us), Llc | Methods and apparatus to monitor impressions of social media messages |
US10333882B2 (en) | 2013-08-28 | 2019-06-25 | The Nielsen Company (Us), Llc | Methods and apparatus to estimate demographics of users employing social media |
US8910195B1 (en) | 2014-02-20 | 2014-12-09 | Google Inc. | Systems and methods for enhancing audience measurement data |
US20160189181A1 (en) | 2014-12-29 | 2016-06-30 | The Nielsen Company (Us), Llc | Methods and apparatus to estimate demographics of an audience of a media event using social media message sentiment |
-
2013
- 2013-12-27 US US14/142,411 patent/US10333882B2/en active Active
-
2014
- 2014-08-25 KR KR1020177003503A patent/KR102355826B1/en active IP Right Grant
- 2014-08-25 AU AU2014311451A patent/AU2014311451A1/en not_active Abandoned
- 2014-08-25 JP JP2015549875A patent/JP6115901B2/en not_active Expired - Fee Related
- 2014-08-25 CN CN201480002842.9A patent/CN104756504A/en active Pending
- 2014-08-25 KR KR1020217000403A patent/KR102347083B1/en active IP Right Grant
- 2014-08-25 KR KR1020217043299A patent/KR102378855B1/en active IP Right Grant
- 2014-08-25 CA CA2889349A patent/CA2889349C/en active Active
- 2014-08-25 KR KR1020157010954A patent/KR101706745B1/en active IP Right Grant
- 2014-08-25 EP EP14839065.1A patent/EP3039875A4/en not_active Withdrawn
- 2014-08-25 WO PCT/US2014/052537 patent/WO2015031262A1/en active Application Filing
- 2014-08-25 BR BR112015009526A patent/BR112015009526A2/en active Search and Examination
-
2015
- 2015-12-24 HK HK15112719.8A patent/HK1212130A1/en unknown
-
2019
- 2019-06-24 US US16/450,440 patent/US11496433B2/en active Active
Also Published As
Publication number | Publication date |
---|---|
US11496433B2 (en) | 2022-11-08 |
HK1212130A1 (en) | 2016-06-03 |
US20190379629A1 (en) | 2019-12-12 |
KR102355826B1 (en) | 2022-01-26 |
JP6115901B2 (en) | 2017-04-19 |
CN104756504A (en) | 2015-07-01 |
EP3039875A4 (en) | 2017-03-22 |
CA2889349A1 (en) | 2015-03-05 |
KR101706745B1 (en) | 2017-02-14 |
BR112015009526A2 (en) | 2019-12-17 |
KR102347083B1 (en) | 2022-01-04 |
KR20170018467A (en) | 2017-02-17 |
US10333882B2 (en) | 2019-06-25 |
WO2015031262A1 (en) | 2015-03-05 |
US20150067075A1 (en) | 2015-03-05 |
EP3039875A1 (en) | 2016-07-06 |
KR20150067224A (en) | 2015-06-17 |
AU2014311451A1 (en) | 2015-05-14 |
KR102378855B1 (en) | 2022-03-25 |
KR20210006505A (en) | 2021-01-18 |
KR20220003661A (en) | 2022-01-10 |
JP2016505975A (en) | 2016-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11496433B2 (en) | Methods and apparatus to estimate demographics of users employing social media | |
US10803475B2 (en) | Methods and apparatus to compensate for server-generated errors in database proprietor impression data due to misattribution and/or non-coverage | |
US11562394B2 (en) | Methods and apparatus to associate transactions with media impressions | |
US20230283820A1 (en) | Methods and apparatus to identify co-relationships between media using social media | |
US20170011420A1 (en) | Methods and apparatus to analyze and adjust age demographic information | |
US20160189181A1 (en) | Methods and apparatus to estimate demographics of an audience of a media event using social media message sentiment | |
WO2021231419A1 (en) | Methods and apparatus for multi-account adjustment in third-party privacy-protected cloud environments | |
US20150245110A1 (en) | Management of invitational content during broadcasting of media streams |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
EEER | Examination request |
Effective date: 20150414 |
|
EEER | Examination request |
Effective date: 20150414 |